Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense_h_to_4h",
     "dense",
-    "dense_4h_to_h",
-    "query_key_value"
+    "dense_h_to_4h",
+    "query_key_value",
+    "dense_4h_to_h"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7881b57f2735187922f04266024ff36b0c622f732e8f87beaece3d5d21d4f416
+oid sha256:6faee730109822af4b455e885160385e8beb748044e2518b2ebbf6a1ab779dc1
 size 4731640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8714652b5e1d43b872ebaca3f3251c60e6ee85e680fcce17fab5c9f9a411175
+oid sha256:4b3a9780a925e05682faf44a23fccfcf2e5d8436244a420a38126f1161ad9600
 size 2505722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31fb365ee0c96264bdea9c657c19e89e8e5c9056da2a925c115d16c4080c998
+oid sha256:10d73968f801f97bbc44a97b80d868e05a38a84f65ca06a125cca65fb5147d82
 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": 0.00016275379419782723,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0021157993245717543,
+  "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": 0.00016275379419782723,
       "eval_loss": 3.2320632934570312,
-      "eval_runtime": 30.0738,
-      "eval_samples_per_second": 86.055,
-      "eval_steps_per_second": 43.027,
+      "eval_runtime": 30.9159,
+      "eval_samples_per_second": 83.711,
+      "eval_steps_per_second": 41.856,
       "step": 1
+    },
+    {
+      "epoch": 0.0008137689709891362,
+      "grad_norm": 234.95375061035156,
+      "learning_rate": 5e-05,
+      "loss": 12.9234,
+      "step": 5
+    },
+    {
+      "epoch": 0.0016275379419782724,
+      "grad_norm": 265.54571533203125,
+      "learning_rate": 0.0001,
+      "loss": 13.0763,
+      "step": 10
+    },
+    {
+      "epoch": 0.0016275379419782724,
+      "eval_loss": 3.215762138366699,
+      "eval_runtime": 30.0768,
+      "eval_samples_per_second": 86.046,
+      "eval_steps_per_second": 43.023,
+      "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": 3068783493120.0,
+  "total_flos": 40661381283840.0,
   "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 sha256:10570ca0e2fa3e6e24346016cc3b11d1c7828ecede2601a62692549927e523f0
+oid sha256:f015369437b23fbccc47b6ebf22ef40866d869f1a285a1fe4700787c9906ce54
 size 6776