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",
     "query_key_value",
     "dense",
-    "dense_4h_to_h"
+    "dense_4h_to_h",
+    "dense_h_to_4h"
   ],
   "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:d4c84ce6ee51fbafdd5f6453b40dd4587a137bceeb243dc0f5e2ab6e99fc10ba
+oid sha256:bb32d1ca8869d64e77ee850a920db6d61737f2c669604676ba7649bd6cc8f539
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e87282cf99ce3219780a3bbbb0d4c5b7cfcb8c59ce0d19ee2083cdcfd4a2118
+oid sha256:4fad77e538c99b0ddee232693f542a2d80008020f69e1884e673b1b2e4700aa2
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c7f3ed21123fdd8f21612f481495bda24e605b27dfc3d51d2d0d8c90c2de4d
+oid sha256:f918e894c61d79473825b52a272cf41e854c27a6d9183f7c13da913c2b3b6227
 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": 0.00044296788482834997,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005758582502768549,
+  "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": 0.00044296788482834997,
       "eval_loss": 1.6710176467895508,
-      "eval_runtime": 54.7254,
-      "eval_samples_per_second": 17.378,
-      "eval_steps_per_second": 8.698,
+      "eval_runtime": 54.8379,
+      "eval_samples_per_second": 17.342,
+      "eval_steps_per_second": 8.68,
       "step": 1
+    },
+    {
+      "epoch": 0.0022148394241417496,
+      "grad_norm": 1.1933499574661255,
+      "learning_rate": 5e-05,
+      "loss": 6.0533,
+      "step": 5
+    },
+    {
+      "epoch": 0.004429678848283499,
+      "grad_norm": 1.8788539171218872,
+      "learning_rate": 0.0001,
+      "loss": 7.0404,
+      "step": 10
+    },
+    {
+      "epoch": 0.004429678848283499,
+      "eval_loss": 1.621188759803772,
+      "eval_runtime": 53.4644,
+      "eval_samples_per_second": 17.788,
+      "eval_steps_per_second": 8.903,
+      "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": 163247803072512.0,
+  "total_flos": 2122221439942656.0,
   "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:a513d39671eb34128523dddd1881c6c52b0883a715f37cb507a1ffd387fc5a80
+oid sha256:5727b1e0c3905eaf086a00c6f7232d10f927b3bcb22bf2328703d480c7885dbc
 size 6776