Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
+    "up_proj",
     "o_proj",
-    "k_proj",
+    "v_proj",
     "q_proj",
-    "up_proj",
     "down_proj",
+    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf9b0d49cf265c07a87201b53eab8e67bed8f88485ba6358c9fa71aab713a69
+oid sha256:90fd27d3f7e1de3a6af278862fe2192c458ba7d74d061cb2ebe342c9d2ecea00
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef26e5e5205f158f6e7289ea7680044720c473c09bd7ecd8b7fad76878ba161
+oid sha256:dcf1afb19bbba22551452bbbec93402adec83b9f2f9f678d3d013656d9d37034
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:3f0082b9ee265cb0c6910d3944f6a738794d996da2e7f7ac5ed1f97dde094437
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010471204188481676,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.013612565445026177,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0010471204188481676,
       "eval_loss": 1.86158287525177,
-      "eval_runtime": 27.6405,
-      "eval_samples_per_second": 14.58,
-      "eval_steps_per_second": 7.308,
+      "eval_runtime": 27.6088,
+      "eval_samples_per_second": 14.597,
+      "eval_steps_per_second": 7.316,
       "step": 1
+    },
+    {
+      "epoch": 0.005235602094240838,
+      "grad_norm": 0.8584698438644409,
+      "learning_rate": 5e-05,
+      "loss": 1.8245,
+      "step": 5
+    },
+    {
+      "epoch": 0.010471204188481676,
+      "grad_norm": 0.7257477641105652,
+      "learning_rate": 0.0001,
+      "loss": 1.8498,
+      "step": 10
+    },
+    {
+      "epoch": 0.010471204188481676,
+      "eval_loss": 1.7575271129608154,
+      "eval_runtime": 28.1177,
+      "eval_samples_per_second": 14.333,
+      "eval_steps_per_second": 7.184,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 184959646040064.0,
+  "total_flos": 2543195133050880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:501f204214c8f49df076b04fea64dc6730223862fa63c5207ca2fd10687a54e5
+oid sha256:c2077d03ff12c1783371a68507fe62612ff830c88fc987cf55f3a3cff7637254
 size 6776