Training in progress, step 15, checkpoint

last-checkpoint/adapter_config.json

@@ -22,10 +22,10 @@
   "target_modules": [
     "o_proj",
     "v_proj",
+    "k_proj",
     "down_proj",
-    "gate_proj",
     "up_proj",
-    "k_proj",
+    "gate_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1a836c10af7b629bbc48e3d574fb49130cb4983c382e887910afce82cc83f08
+oid sha256:9878148640a6b2701734449a5dd6848af54b0d612d8eb174ee6b52eee7ba1a2b
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f210586a9d92bf4238023a03f11c4b560805dcca67b9f2701fa1fa1729cc88b
+oid sha256:789296e2aae6020b71c4ecb0490363fca7aab82e522800132180fe75afc353d7
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc2035bab756acefcae8b1aa9d2e94c4d32469eb7c31b771e2868cd37ea6f084
+oid sha256:4a75d7f0a1110bb7ddac6881490c0ad001206dbfbcb43220dcaada04d94f78c7
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae215b06cef7ce8b14189a78df633f99142f6a347ad6d9ca4407698465150f9f
+oid sha256:d44d91ef34966a9236815f68477ab8b7c0e58ef42a28a5a22af7e3d0cde110f8
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4768230e2c56e333a2c1ef97ec0fdb63938bf4c4cae7411e5b401bc4f40874
+oid sha256:0ea15c7c7180fa009ae4e9ae36bc8881b572608ebcc3ce285a7736b0f9095f73
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c479cd731589ebc3c48a8922ddaaf8550221ee7e1496d89721342a8c1f3181
+oid sha256:47bdf74ddba6667c73ef9c6fa16a7d1bad165641219424ed3e8eb85032cf718c
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:170a57fd4cccd049a602874563056844faa7b36192d5674f74f3384aca284076
+oid sha256:8f2470a144228bd202c07df4002bbd7fcbc4a4222f4d74493ca1edaeff6a93ee
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f63067c46de31d869f80737ba83996aa5865fbc83e8d5209f41ce77d2bb7663
+oid sha256:3c11c326af75c12615a95cec1905a2e8bc00fae99f6eca9757b169af3d765dc5
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a5b43ce2b1e9cc849f7cc5b9e5408838f896e4252b23bb1ff3ce661b7f9e65
+oid sha256:855a78294165307b2b2b80f48d1cd373054c685f191380eb9daa248b34ff6405
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c9fc68417005f295fcb64bffd3a705ce6d7136bbd381662814aaf99c7220ab2
+oid sha256:82eb7125a98e578fab3e4b9b4b0732f1974838daab66a58369b34c9560151e2d
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
+oid sha256:61d24ba7ec590426989e38648fb3af9ae90cfcee84014eb4dfc33924d7868044
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.035842293906810034,
+  "epoch": 0.053763440860215055,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,89 +18,132 @@
     {
       "epoch": 0.0035842293906810036,
       "eval_loss": 1.371159315109253,
-      "eval_runtime": 8.3908,
-      "eval_samples_per_second": 56.014,
-      "eval_steps_per_second": 7.032,
+      "eval_runtime": 8.0828,
+      "eval_samples_per_second": 58.148,
+      "eval_steps_per_second": 7.299,
       "step": 1
     },
     {
       "epoch": 0.007168458781362007,
-      "grad_norm": 1.1762983798980713,
+      "grad_norm": 1.2307049036026,
       "learning_rate": 2e-05,
       "loss": 1.2685,
       "step": 2
     },
     {
       "epoch": 0.010752688172043012,
-      "grad_norm": 0.999072253704071,
+      "grad_norm": 1.0430188179016113,
       "learning_rate": 4e-05,
       "loss": 1.1567,
       "step": 3
     },
     {
       "epoch": 0.014336917562724014,
-      "grad_norm": 1.0890846252441406,
+      "grad_norm": 1.1231369972229004,
       "learning_rate": 6e-05,
-      "loss": 1.2905,
+      "loss": 1.29,
       "step": 4
     },
     {
       "epoch": 0.017921146953405017,
-      "grad_norm": 1.1394107341766357,
+      "grad_norm": 1.1865134239196777,
       "learning_rate": 8e-05,
-      "loss": 1.2343,
+      "loss": 1.2327,
       "step": 5
     },
     {
       "epoch": 0.017921146953405017,
-      "eval_loss": 1.3072917461395264,
-      "eval_runtime": 8.5738,
-      "eval_samples_per_second": 54.818,
-      "eval_steps_per_second": 6.881,
+      "eval_loss": 1.304574728012085,
+      "eval_runtime": 8.1943,
+      "eval_samples_per_second": 57.357,
+      "eval_steps_per_second": 7.2,
       "step": 5
     },
     {
       "epoch": 0.021505376344086023,
-      "grad_norm": 1.2360237836837769,
+      "grad_norm": 1.2747498750686646,
       "learning_rate": 0.0001,
-      "loss": 1.4268,
+      "loss": 1.4252,
       "step": 6
     },
     {
       "epoch": 0.025089605734767026,
-      "grad_norm": 0.9018695950508118,
+      "grad_norm": 0.9193595051765442,
       "learning_rate": 0.00012,
-      "loss": 1.0908,
+      "loss": 1.0889,
       "step": 7
     },
     {
       "epoch": 0.02867383512544803,
       "grad_norm": NaN,
       "learning_rate": 0.00012,
-      "loss": 1.4248,
+      "loss": 1.4204,
       "step": 8
     },
     {
       "epoch": 0.03225806451612903,
-      "grad_norm": 0.8699414134025574,
+      "grad_norm": 0.8832981586456299,
       "learning_rate": 0.00014,
-      "loss": 1.1859,
+      "loss": 1.1822,
       "step": 9
     },
     {
       "epoch": 0.035842293906810034,
-      "grad_norm": 0.7875003218650818,
+      "grad_norm": 0.804837703704834,
       "learning_rate": 0.00016,
-      "loss": 1.1898,
+      "loss": 1.1865,
       "step": 10
     },
     {
       "epoch": 0.035842293906810034,
-      "eval_loss": 1.1698945760726929,
-      "eval_runtime": 8.6367,
-      "eval_samples_per_second": 54.419,
-      "eval_steps_per_second": 6.831,
+      "eval_loss": 1.1667453050613403,
+      "eval_runtime": 8.2688,
+      "eval_samples_per_second": 56.84,
+      "eval_steps_per_second": 7.135,
       "step": 10
+    },
+    {
+      "epoch": 0.03942652329749104,
+      "grad_norm": 1.0118783712387085,
+      "learning_rate": 0.00018,
+      "loss": 1.1729,
+      "step": 11
+    },
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 0.9140554070472717,
+      "learning_rate": 0.0002,
+      "loss": 1.0825,
+      "step": 12
+    },
+    {
+      "epoch": 0.04659498207885305,
+      "grad_norm": 0.9855129718780518,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 1.1756,
+      "step": 13
+    },
+    {
+      "epoch": 0.05017921146953405,
+      "grad_norm": 0.7907399535179138,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.0081,
+      "step": 14
+    },
+    {
+      "epoch": 0.053763440860215055,
+      "grad_norm": 0.809781014919281,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 0.9997,
+      "step": 15
+    },
+    {
+      "epoch": 0.053763440860215055,
+      "eval_loss": 1.1061427593231201,
+      "eval_runtime": 8.2438,
+      "eval_samples_per_second": 57.012,
+      "eval_steps_per_second": 7.157,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8334163920814080.0,
+  "total_flos": 1.250124588122112e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad82ad32525e933af8b9fc0db6dec8e95c1d489a1adc2b0fa6be91ccfcf9268
+oid sha256:80e50aba904d39c5864e0f36c27d2c58f2cca1afdba552845d8b36d9735033ed
 size 6712