Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query_key_value",
-    "dense_h_to_4h",
     "dense_4h_to_h",
-    "dense"
+    "dense",
+    "query_key_value",
+    "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 sha256:380cd211afeb883a38fa9f61d4e84998b34b54e570dba43dfafeb56f42131d64
+oid sha256:6b93e5bd75b575e6e88f5e54747692cc658d8c0ffc173de276a183558eec11a8
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120362bc20968ec8b1c7402c508f5c4eab528fea48d755d9bf5d3041cc93b73b
+oid sha256:caefd9faa605619008e57cbbd0df85b8f2e8b808d4168b750dab18e0851e3030
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0b367b3e9d37cf71573bf88c375c76ae6cfcee3c2fe025f9a39fc33da8562fc
+oid sha256:9aff36119180d11672e5f41239d75959a6cc53a2997d91aee1bbc1f32b00c958
 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": 7.541620317125135e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009804106412262675,
+  "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": 7.541620317125135e-05,
       "eval_loss": 1.8562190532684326,
-      "eval_runtime": 901.8409,
-      "eval_samples_per_second": 6.192,
-      "eval_steps_per_second": 3.096,
+      "eval_runtime": 900.2586,
+      "eval_samples_per_second": 6.203,
+      "eval_steps_per_second": 3.101,
       "step": 1
+    },
+    {
+      "epoch": 0.0003770810158562567,
+      "grad_norm": 4.088282108306885,
+      "learning_rate": 5e-05,
+      "loss": 7.7757,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007541620317125134,
+      "grad_norm": 5.26944637298584,
+      "learning_rate": 0.0001,
+      "loss": 6.9662,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007541620317125134,
+      "eval_loss": 1.3146437406539917,
+      "eval_runtime": 903.0345,
+      "eval_samples_per_second": 6.184,
+      "eval_steps_per_second": 3.092,
+      "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": 570561071677440.0,
+  "total_flos": 7345973797847040.0,
   "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 sha256:74d6fbbaa205f1e791e6957861726e8c746e3dc78bac05feb72feddf028de4a9
+oid sha256:8b9d29094fa89251ff93125a64a86c78de0cc1603eaf5550600dc3705f72a400
 size 6776