Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "gate_proj",
-    "o_proj",
     "down_proj",
     "q_proj",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "up_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0bb8d5c5c774aed6924ba5ef04cb5b8d3996d972c292adfbec843432b204b1
+oid sha256:070c30adca6371f6a384d53962e112fcf9b06f47053bd9b25e15cf89ba0b22b2
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f027f8b336f29b9c1d756e62e354cb0920a317cce3db537bfc5bf60f06927f8
+oid sha256:85f8e9d8d4d524ae022cbf81d218c6a78bc66668ee263a86f82811dad527e97e
 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

@@ -1,16 +1,16 @@
 {
   "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": 0.01440234761685133,
+      "grad_norm": 0.015242994762957096,
       "learning_rate": 2e-05,
       "loss": 11.9315,
       "step": 1
@@ -18,21 +18,21 @@
     {
       "epoch": 0.0005608524957936063,
       "eval_loss": 11.931306838989258,
-      "eval_runtime": 2.6444,
-      "eval_samples_per_second": 283.993,
-      "eval_steps_per_second": 142.186,
+      "eval_runtime": 2.6767,
+      "eval_samples_per_second": 280.572,
+      "eval_steps_per_second": 140.473,
       "step": 1
     },
     {
       "epoch": 0.0011217049915872126,
-      "grad_norm": 0.008986671455204487,
+      "grad_norm": 0.00954145472496748,
       "learning_rate": 4e-05,
       "loss": 11.9304,
       "step": 2
     },
     {
       "epoch": 0.0016825574873808188,
-      "grad_norm": 0.013879197649657726,
+      "grad_norm": 0.014847060665488243,
       "learning_rate": 6e-05,
       "loss": 11.9319,
       "step": 3
@@ -40,75 +40,10 @@
     {
       "epoch": 0.0016825574873808188,
       "eval_loss": 11.931303977966309,
-      "eval_runtime": 2.6803,
-      "eval_samples_per_second": 280.195,
-      "eval_steps_per_second": 140.284,
+      "eval_runtime": 2.7161,
+      "eval_samples_per_second": 276.496,
+      "eval_steps_per_second": 138.432,
       "step": 3
-    },
-    {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.01761799305677414,
-      "learning_rate": 8e-05,
-      "loss": 11.9328,
-      "step": 4
-    },
-    {
-      "epoch": 0.0028042624789680315,
-      "grad_norm": 0.018328625708818436,
-      "learning_rate": 0.0001,
-      "loss": 11.9248,
-      "step": 5
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.009327949024736881,
-      "learning_rate": 0.00012,
-      "loss": 11.926,
-      "step": 6
-    },
-    {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.931290626525879,
-      "eval_runtime": 2.7752,
-      "eval_samples_per_second": 270.606,
-      "eval_steps_per_second": 135.483,
-      "step": 6
-    },
-    {
-      "epoch": 0.003925967470555244,
-      "grad_norm": 0.011274761520326138,
-      "learning_rate": 0.00014,
-      "loss": 11.9324,
-      "step": 7
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.0072128307074308395,
-      "learning_rate": 0.00016,
-      "loss": 11.935,
-      "step": 8
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "grad_norm": 0.013769167475402355,
-      "learning_rate": 0.00018,
-      "loss": 11.9287,
-      "step": 9
-    },
-    {
-      "epoch": 0.005047672462142457,
-      "eval_loss": 11.931265830993652,
-      "eval_runtime": 2.7062,
-      "eval_samples_per_second": 277.515,
-      "eval_steps_per_second": 138.942,
-      "step": 9
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.008655436336994171,
-      "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 sha256:6deb7d8ed72edeb3adc757a9f5370f2248de027bb1c9ca4498888ded15ce7592
+oid sha256:c05dd79855f3d1e2471adce21335d03b6dade5be86d74b45ff7774462a74ac71
 size 6776