Training in progress, step 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
-    "down_proj",
     "gate_proj",
+    "down_proj",
+    "up_proj",
     "k_proj",
-    "q_proj",
-    "up_proj"
+    "o_proj",
+    "v_proj",
+    "q_proj"
   ],
   "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:f58663ed814f0b1cd69cb14cc00f196d9a2dc6a2d7696e9b2f835f260421367e
+oid sha256:a6fe2ae351a26428956ad8197aad5f7770937aa85743f87836e1b63483e09a97
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea064b0ad453ac60cdc6f673c03b34f65b504a08f8b7ccbf08ee735acf79a544
+oid sha256:3c496a8f5da9338b868753d4540661ed4db526043d0743bf915375d13b7bccca
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb42603c6ea93282cd7b812e4230cfeb74ceecfc7f6b103a7e0220f43cb7ac48
+oid sha256:02778d82e51b54b5f033cecc109c4bb6bbe105f986998706dc99ddcab7146d99
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05333333333333334,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.26666666666666666,
+  "eval_steps": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.05333333333333334,
       "eval_loss": 7.436699867248535,
-      "eval_runtime": 0.802,
-      "eval_samples_per_second": 9.975,
-      "eval_steps_per_second": 4.988,
+      "eval_runtime": 0.8118,
+      "eval_samples_per_second": 9.855,
+      "eval_steps_per_second": 4.927,
       "step": 1
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_loss": 7.368486404418945,
+      "eval_runtime": 0.3612,
+      "eval_samples_per_second": 22.148,
+      "eval_steps_per_second": 11.074,
+      "step": 4
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 19.62460708618164,
+      "learning_rate": 5e-05,
+      "loss": 7.5589,
+      "step": 5
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 19,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 1,
+  "num_train_epochs": 2,
+  "save_steps": 5,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 32429825851392.0,
+  "total_flos": 162149129256960.0,
   "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 sha256:89b5bd2f195c6b8a4c2904912770cb9a5fe0289389c4fcc406eebd21c48ea5f4
+oid sha256:d038b07b01102c4caaa5a897e722865c9cb29e9b96eeeb681943f4ad65bb17f7
 size 6776