Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,9 +20,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "dense",
     "query_key_value",
     "dense_4h_to_h",
+    "dense",
     "dense_h_to_4h"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9078a52db19b470ba6bbce68db89f22174bf8443ad82159129e32192a706f25b
+oid sha256:1e0448d3e02d40bfa4827bf93d4b865ce9fec73a06c7f269db8663facacc3baf
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3e81f368a9f9ece9d39f743bf2bb44ea9a06791bb9e9b34ac735a2f5cfe93e
+oid sha256:38ca91fef53ead4a36f1aa3aca3757831c1bb88d4080a07f57be7b4ab7637164
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b3f32ce9472813d7cc4998dd6f54d487ccf79d88132a529ec2b28324f14a0f2
+oid sha256:8586512a4566a393800b83e344d6730e6751cb11be4ad93fd9de02ed9e47b01f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04830917874396135,
+  "epoch": 0.014492753623188406,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.004830917874396135,
-      "grad_norm": 4.588574409484863,
+      "grad_norm": 4.699305534362793,
       "learning_rate": 2e-05,
       "loss": 44.3766,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.004830917874396135,
       "eval_loss": 11.088024139404297,
-      "eval_runtime": 1.8991,
-      "eval_samples_per_second": 46.338,
-      "eval_steps_per_second": 23.169,
+      "eval_runtime": 1.9009,
+      "eval_samples_per_second": 46.294,
+      "eval_steps_per_second": 23.147,
       "step": 1
     },
     {
       "epoch": 0.00966183574879227,
-      "grad_norm": 4.322054862976074,
+      "grad_norm": 4.3816046714782715,
       "learning_rate": 4e-05,
       "loss": 44.3588,
       "step": 2
     },
     {
       "epoch": 0.014492753623188406,
-      "grad_norm": 5.047557353973389,
+      "grad_norm": 5.163635730743408,
       "learning_rate": 6e-05,
-      "loss": 44.4384,
+      "loss": 44.4378,
       "step": 3
     },
     {
       "epoch": 0.014492753623188406,
-      "eval_loss": 11.081047058105469,
-      "eval_runtime": 1.5273,
-      "eval_samples_per_second": 57.619,
-      "eval_steps_per_second": 28.81,
+      "eval_loss": 11.081073760986328,
+      "eval_runtime": 1.5264,
+      "eval_samples_per_second": 57.653,
+      "eval_steps_per_second": 28.826,
       "step": 3
-    },
-    {
-      "epoch": 0.01932367149758454,
-      "grad_norm": 4.04183292388916,
-      "learning_rate": 8e-05,
-      "loss": 44.3261,
-      "step": 4
-    },
-    {
-      "epoch": 0.024154589371980676,
-      "grad_norm": 4.250118255615234,
-      "learning_rate": 0.0001,
-      "loss": 44.298,
-      "step": 5
-    },
-    {
-      "epoch": 0.028985507246376812,
-      "grad_norm": 3.9748477935791016,
-      "learning_rate": 0.00012,
-      "loss": 44.2598,
-      "step": 6
-    },
-    {
-      "epoch": 0.028985507246376812,
-      "eval_loss": 11.053829193115234,
-      "eval_runtime": 1.5763,
-      "eval_samples_per_second": 55.828,
-      "eval_steps_per_second": 27.914,
-      "step": 6
-    },
-    {
-      "epoch": 0.033816425120772944,
-      "grad_norm": 4.778048992156982,
-      "learning_rate": 0.00014,
-      "loss": 44.2285,
-      "step": 7
-    },
-    {
-      "epoch": 0.03864734299516908,
-      "grad_norm": 4.494859218597412,
-      "learning_rate": 0.00016,
-      "loss": 44.1229,
-      "step": 8
-    },
-    {
-      "epoch": 0.043478260869565216,
-      "grad_norm": 4.587972164154053,
-      "learning_rate": 0.00018,
-      "loss": 44.1111,
-      "step": 9
-    },
-    {
-      "epoch": 0.043478260869565216,
-      "eval_loss": 11.003266334533691,
-      "eval_runtime": 1.58,
-      "eval_samples_per_second": 55.697,
-      "eval_steps_per_second": 27.849,
-      "step": 9
-    },
-    {
-      "epoch": 0.04830917874396135,
-      "grad_norm": 4.518380641937256,
-      "learning_rate": 0.0002,
-      "loss": 44.0229,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +58,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 831982141440.0,
+  "total_flos": 249594642432.0,
   "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 sha256:30da54057396157b96f3c452627f2952804e2e919866f5b5017a71b955e48f46
+oid sha256:9bac14f75cfb45a21f62f3dc218d739e19298174d09f122c55037b7500ae1dc2
 size 6776