Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "gate_proj",
-    "v_proj",
     "down_proj",
+    "gate_proj",
     "q_proj",
     "o_proj",
-    "k_proj"
+    "k_proj",
+    "v_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 sha256:485310065b35e6d352ca48a6a232f032cb6e70ff52d7829fb9f2d90394d03471
+oid sha256:d3357c8cb9da34a3a34bfb9a549ce78ffdb666ac716f5c8c0bc1bd8ee2f9588d
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c21916eae43d59ca0ba3b7f231b54009e17b1392c1e85df3194665678b539e2
+oid sha256:7a18d955bf2e803d99ac3eecaa89e7c8ec2653653557f237bbf61f1b015197f9
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106d2362bc2f5d0877cb3549f0a8edc5f2a3f7ece3ea2591042b0fa260c47153
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 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": 0.0008382229673093043,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010896898575020955,
+  "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": 0.0008382229673093043,
       "eval_loss": 10.376425743103027,
-      "eval_runtime": 6.1317,
-      "eval_samples_per_second": 82.032,
-      "eval_steps_per_second": 41.098,
+      "eval_runtime": 6.0687,
+      "eval_samples_per_second": 82.885,
+      "eval_steps_per_second": 41.525,
       "step": 1
+    },
+    {
+      "epoch": 0.004191114836546521,
+      "grad_norm": 3.966305732727051,
+      "learning_rate": 5e-05,
+      "loss": 10.3163,
+      "step": 5
+    },
+    {
+      "epoch": 0.008382229673093043,
+      "grad_norm": 3.3468010425567627,
+      "learning_rate": 0.0001,
+      "loss": 9.9714,
+      "step": 10
+    },
+    {
+      "epoch": 0.008382229673093043,
+      "eval_loss": 10.273557662963867,
+      "eval_runtime": 6.0619,
+      "eval_samples_per_second": 82.978,
+      "eval_steps_per_second": 41.571,
+      "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": 98337816576.0,
+  "total_flos": 1425898340352.0,
   "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:bcc0929ae0acc061396992d9abc7c740a72e510158a35132121671f0dae97824
+oid sha256:621845d5ccf6295cb0695ac75d34cb8cffebfab95c71d1f8a7e8b03ae255bdf6
 size 6776