Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
+    "o_proj",
     "v_proj",
-    "down_proj",
     "k_proj",
-    "up_proj",
+    "down_proj",
+    "gate_proj",
     "q_proj",
-    "o_proj"
+    "up_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 sha256:4f2ef4015133f805583bcc122741673ff93a07daabd8c78efca1dabca40ef83a
+oid sha256:e5ee48b4168e92aeb847b9c8215e9d150c73603ab1dc297fb4d288cdca4a4d67
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d86c5ac5f30e6dfe96501016235b40b0e40b311fee1d5758d3d27bb886603505
+oid sha256:927a8bba022103acd7157294f53242f6f0084d5fcddafe00a576f42aacd81fe9
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
+oid sha256:464e6cdff3f8548ba79ace3859c72e6b06d1e045e69932eb75c584ad0e8918c8
 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

@@ -1,114 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005608524957936063,
+  "epoch": 0.0016825574873808188,
   "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": 0.0005608524957936063,
-      "grad_norm": 0.01444172766059637,
+      "grad_norm": 0.012741726823151112,
       "learning_rate": 2e-05,
       "loss": 11.9315,
       "step": 1
     },
     {
       "epoch": 0.0005608524957936063,
-      "eval_loss": 11.931306838989258,
-      "eval_runtime": 2.6938,
-      "eval_samples_per_second": 278.791,
-      "eval_steps_per_second": 139.581,
+      "eval_loss": 11.931304931640625,
+      "eval_runtime": 2.7285,
+      "eval_samples_per_second": 275.238,
+      "eval_steps_per_second": 137.802,
       "step": 1
     },
     {
       "epoch": 0.0011217049915872126,
-      "grad_norm": 0.008981737308204174,
+      "grad_norm": 0.008430744521319866,
       "learning_rate": 4e-05,
       "loss": 11.9304,
       "step": 2
     },
     {
       "epoch": 0.0016825574873808188,
-      "grad_norm": 0.015570709481835365,
+      "grad_norm": 0.013430982828140259,
       "learning_rate": 6e-05,
       "loss": 11.9319,
       "step": 3
     },
     {
       "epoch": 0.0016825574873808188,
-      "eval_loss": 11.931303977966309,
-      "eval_runtime": 2.706,
-      "eval_samples_per_second": 277.532,
-      "eval_steps_per_second": 138.951,
+      "eval_loss": 11.931302070617676,
+      "eval_runtime": 2.7365,
+      "eval_samples_per_second": 274.435,
+      "eval_steps_per_second": 137.4,
       "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.016449356451630592,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.018278617411851883,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.008942726068198681,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.93128776550293,
-      "eval_runtime": 2.7321,
-      "eval_samples_per_second": 274.885,
-      "eval_steps_per_second": 137.625,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.010885247960686684,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.007305529434233904,
-      "learning_rate": 0.00016,
-      "loss": 11.935,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.014387518167495728,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.93126106262207,
-      "eval_runtime": 2.6381,
-      "eval_samples_per_second": 284.669,
-      "eval_steps_per_second": 142.524,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.008650769479572773,
-      "learning_rate": 0.0002,
-      "loss": 11.9335,
-      "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": 1211154432.0,
+  "total_flos": 384024576.0,
   "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:ed06b137b37a62a6de09814c822a220062a424277456c1e461b887a3d36470db
+oid sha256:9f94f4d537f06c8dc38a983c176d07a34ca3e1927e872c953008eb983464a91f
 size 6776