Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "fc1",
+    "k_proj",
     "dense",
     "v_proj",
-    "k_proj",
-    "fc1",
-    "fc2",
-    "q_proj"
+    "fc2"
   ],
   "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 sha256:3b65a331dd0da5cd3c5055eb60b93e6cce51c303def33b05bbe94bf0a70f55aa
+oid sha256:0d9fc2f5febb28b5dc9963c4e5b0619159698e00ca630fb1687197e1a9cb7bc1
 size 47235968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30be8471c7db8b4e89a53be3a4fc0f1c0f5bce4fdb14b308d4892a787b2a7580
+oid sha256:3d77a569722159cdfd3bab3f095dde5ac7acd99bb6fc6e0d03b4de423db5a37e
 size 24410836

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde21f1c16f25c66b9b001f2dd5d8a90b5d473a83d33d628f5e350b25b693174
+oid sha256:0e78d3658e0851a4ee41d5a1113d681dfde5cfaa7acf2d176c9323579d77c0ff
 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": 0.0001389274798555154,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0018060572381217005,
+  "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": 0.0001389274798555154,
       "eval_loss": 1.242689609527588,
-      "eval_runtime": 245.5928,
-      "eval_samples_per_second": 12.342,
-      "eval_steps_per_second": 6.173,
+      "eval_runtime": 245.9055,
+      "eval_samples_per_second": 12.326,
+      "eval_steps_per_second": 6.165,
       "step": 1
+    },
+    {
+      "epoch": 0.0006946373992775772,
+      "grad_norm": 2.261873722076416,
+      "learning_rate": 5e-05,
+      "loss": 1.1573,
+      "step": 5
+    },
+    {
+      "epoch": 0.0013892747985551543,
+      "grad_norm": 2.256624221801758,
+      "learning_rate": 0.0001,
+      "loss": 1.2028,
+      "step": 10
+    },
+    {
+      "epoch": 0.0013892747985551543,
+      "eval_loss": 1.2393931150436401,
+      "eval_runtime": 245.6576,
+      "eval_samples_per_second": 12.338,
+      "eval_steps_per_second": 6.171,
+      "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": 114418841026560.0,
+  "total_flos": 1601863774371840.0,
   "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:d191422fb4914618fe1d5ee2a1cbb8667dc8ca242e0258b30e62dd036ae7dfa7
+oid sha256:8d36e55c59fef4ab75a502e8ee1c5053e814dc9304d1e7639def5587e00781eb
 size 6776