Training in progress, step 10, 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 sha256:7b59688d00d19805618787e6be802234edd3efa3cf99c0deac1f04a0c2fa52a8
+oid sha256:23c0192f0dd9534d6ce6f541e70cdce8fe477f7ee9e86e8ed66935e309692d65
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d682e9f0e811d0d92b349c54b3107974538dd75237edfbfdcab777d84cd7667c
+oid sha256:7a6d87feaf71f414dfdd56983f37c39bd85910a211ec6e7364b7054e7b309b88
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab12cf470d4304db95df6463eb7c5fe7c797baef0952b67a51dcddc77b56b681
+oid sha256:cc2035bab756acefcae8b1aa9d2e94c4d32469eb7c31b771e2868cd37ea6f084
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a2dd6377bcf09dcd959581794b08ed01a60573dd038c62567d17de9ac0277c
+oid sha256:ae215b06cef7ce8b14189a78df633f99142f6a347ad6d9ca4407698465150f9f
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fe07b66cafaa88cfffd10ddd6d52341ca16cf4b5e8b1d04b401b50c96edc4aa
+oid sha256:1f4768230e2c56e333a2c1ef97ec0fdb63938bf4c4cae7411e5b401bc4f40874
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2076d1f464f170f03fab2f9a7c261fa693b12040fbe56c6bddedd28d0ea9ec1f
+oid sha256:e0c479cd731589ebc3c48a8922ddaaf8550221ee7e1496d89721342a8c1f3181
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a7731e60badee1a24d17f9a1a07a8e824606314ee209dc052f411499d027d3f
+oid sha256:170a57fd4cccd049a602874563056844faa7b36192d5674f74f3384aca284076
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a14ae95e84ea0ba588effb2a7401990ac5f38536b1198365e31ff56094d5df5
+oid sha256:4f63067c46de31d869f80737ba83996aa5865fbc83e8d5209f41ce77d2bb7663
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f956c2636f62aad58b918239ff1e76cd9d698d42a56e07659f577ce14adf282a
+oid sha256:55a5b43ce2b1e9cc849f7cc5b9e5408838f896e4252b23bb1ff3ce661b7f9e65
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9509aaa911cb8478fdf7704d9effdd33b3d5bf01b67dff4209f6d35961033080
+oid sha256:1c9fc68417005f295fcb64bffd3a705ce6d7136bbd381662814aaf99c7220ab2
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.017921146953405017,
+  "epoch": 0.035842293906810034,
   "eval_steps": 5,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -18,46 +18,89 @@
     {
       "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": 1.2747498750686646,
+      "learning_rate": 0.0001,
+      "loss": 1.4252,
+      "step": 6
+    },
+    {
+      "epoch": 0.025089605734767026,
+      "grad_norm": 0.9193595051765442,
+      "learning_rate": 0.00012,
+      "loss": 1.0889,
+      "step": 7
+    },
+    {
+      "epoch": 0.02867383512544803,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 1.4204,
+      "step": 8
+    },
+    {
+      "epoch": 0.03225806451612903,
+      "grad_norm": 0.8832981586456299,
+      "learning_rate": 0.00014,
+      "loss": 1.1822,
+      "step": 9
+    },
+    {
+      "epoch": 0.035842293906810034,
+      "grad_norm": 0.804837703704834,
+      "learning_rate": 0.00016,
+      "loss": 1.1865,
+      "step": 10
+    },
+    {
+      "epoch": 0.035842293906810034,
+      "eval_loss": 1.1667453050613403,
+      "eval_runtime": 8.2688,
+      "eval_samples_per_second": 56.84,
+      "eval_steps_per_second": 7.135,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4167081960407040.0,
+  "total_flos": 8334163920814080.0,
   "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