Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
+    "o_proj",
     "q_proj",
     "gate_proj",
+    "v_proj",
     "up_proj",
     "k_proj",
-    "o_proj",
-    "v_proj"
+    "down_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:ed6501fcd3c92acbab95f19e52aebaf2c39ffe83bd1161aea334fff7df46734a
+oid sha256:c5db55bd738c77523c1c2964518410715c54bff02af0c01348ab402d2f718727
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef73ca96031027af39d66e05d708d1c06c589bff9417ce8ffcedc778c37c3c2e
+oid sha256:d819f53646231765ceea93df9f79a5d89cb0a6c34c6a00b33295b501582728f2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47a639da18d5756dd329b70270915837be928d52692379b9e5cd01847b059c27
+oid sha256:f9afd89781a51d597dbea42578ed20dd87af91f24b2c8ed574d84057f40bf94d
 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": 0.0005782853838369235,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007517709989880006,
+  "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": 0.0005782853838369235,
       "eval_loss": 0.9053186774253845,
-      "eval_runtime": 52.9415,
-      "eval_samples_per_second": 13.77,
-      "eval_steps_per_second": 6.894,
+      "eval_runtime": 53.0345,
+      "eval_samples_per_second": 13.746,
+      "eval_steps_per_second": 6.882,
       "step": 1
+    },
+    {
+      "epoch": 0.0028914269191846176,
+      "grad_norm": 0.4900228977203369,
+      "learning_rate": 5e-05,
+      "loss": 0.888,
+      "step": 5
+    },
+    {
+      "epoch": 0.005782853838369235,
+      "grad_norm": 0.5391601324081421,
+      "learning_rate": 0.0001,
+      "loss": 0.8614,
+      "step": 10
+    },
+    {
+      "epoch": 0.005782853838369235,
+      "eval_loss": 0.7835583686828613,
+      "eval_runtime": 53.2699,
+      "eval_samples_per_second": 13.685,
+      "eval_steps_per_second": 6.852,
+      "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": 231195531018240.0,
+  "total_flos": 2450672628793344.0,
   "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 sha256:7fb61a5190041f4396ffa8acb0063c6d6261ce430d4589cda83bd3aa3eb6beba
+oid sha256:10c5c5b2e0f138c56219996955c8a67f62288134a9a7215cba71ce4ed801d702
 size 6776