Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4fc91b5b15f5867d1a7cd3e8f087ae342818f37446ea0e462c8829bea9cf83
+oid sha256:153e76b88a3e997cd582fe3173cf216f64f92b10649f1c45302a55d7ee5629ae
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe6fb12c4a7eac7403ae28746ebe4773ef59bd2b81414c2cde757be4b72ab5e
+oid sha256:d64e3406892c1c2ff1ac36d994e0e8be241a0b7918f22b4fe041c4aea8c2f049
 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": 0.011217049915872126,
+  "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": 0.0011217049915872126,
-      "grad_norm": 0.010207759216427803,
+      "epoch": 0.0005608524957936063,
+      "grad_norm": 0.01552088838070631,
       "learning_rate": 2e-05,
-      "loss": 11.9305,
+      "loss": 11.9315,
       "step": 1
     },
     {
-      "epoch": 0.0011217049915872126,
-      "eval_loss": 11.931302070617676,
-      "eval_runtime": 1.5864,
-      "eval_samples_per_second": 473.392,
-      "eval_steps_per_second": 118.506,
+      "epoch": 0.0005608524957936063,
+      "eval_loss": 11.931306838989258,
+      "eval_runtime": 2.6874,
+      "eval_samples_per_second": 279.454,
+      "eval_steps_per_second": 139.913,
       "step": 1
     },
     {
-      "epoch": 0.002243409983174425,
-      "grad_norm": 0.014218014664947987,
+      "epoch": 0.0011217049915872126,
+      "grad_norm": 0.009788701310753822,
       "learning_rate": 4e-05,
-      "loss": 11.9324,
+      "loss": 11.9304,
       "step": 2
     },
     {
-      "epoch": 0.0033651149747616375,
-      "grad_norm": 0.01008047629147768,
+      "epoch": 0.0016825574873808188,
+      "grad_norm": 0.013149156235158443,
       "learning_rate": 6e-05,
-      "loss": 11.9253,
+      "loss": 11.9319,
       "step": 3
     },
     {
-      "epoch": 0.0033651149747616375,
-      "eval_loss": 11.931297302246094,
-      "eval_runtime": 1.6298,
-      "eval_samples_per_second": 460.789,
-      "eval_steps_per_second": 115.351,
+      "epoch": 0.0016825574873808188,
+      "eval_loss": 11.931302070617676,
+      "eval_runtime": 2.7419,
+      "eval_samples_per_second": 273.898,
+      "eval_steps_per_second": 137.131,
       "step": 3
-    },
-    {
-      "epoch": 0.00448681996634885,
-      "grad_norm": 0.005606319755315781,
-      "learning_rate": 8e-05,
-      "loss": 11.9338,
-      "step": 4
-    },
-    {
-      "epoch": 0.005608524957936063,
-      "grad_norm": 0.009023796766996384,
-      "learning_rate": 0.0001,
-      "loss": 11.9314,
-      "step": 5
-    },
-    {
-      "epoch": 0.006730229949523275,
-      "grad_norm": 0.01568673551082611,
-      "learning_rate": 0.00012,
-      "loss": 11.9317,
-      "step": 6
-    },
-    {
-      "epoch": 0.006730229949523275,
-      "eval_loss": 11.931279182434082,
-      "eval_runtime": 1.6377,
-      "eval_samples_per_second": 458.556,
-      "eval_steps_per_second": 114.792,
-      "step": 6
-    },
-    {
-      "epoch": 0.007851934941110488,
-      "grad_norm": 0.016139866784214973,
-      "learning_rate": 0.00014,
-      "loss": 11.927,
-      "step": 7
-    },
-    {
-      "epoch": 0.0089736399326977,
-      "grad_norm": 0.016835955902934074,
-      "learning_rate": 0.00016,
-      "loss": 11.9367,
-      "step": 8
-    },
-    {
-      "epoch": 0.010095344924284913,
-      "grad_norm": 0.01244762446731329,
-      "learning_rate": 0.00018,
-      "loss": 11.9306,
-      "step": 9
-    },
-    {
-      "epoch": 0.010095344924284913,
-      "eval_loss": 11.931243896484375,
-      "eval_runtime": 1.6456,
-      "eval_samples_per_second": 456.359,
-      "eval_steps_per_second": 114.242,
-      "step": 9
-    },
-    {
-      "epoch": 0.011217049915872126,
-      "grad_norm": 0.010091469623148441,
-      "learning_rate": 0.0002,
-      "loss": 11.9328,
-      "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": 2392768512.0,
+  "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:d2ce149ccbf74c75eb8c00802c87066be4e8f73892cf619b77e696423334565d
+oid sha256:217bbbcfe707ed16f5f71cd8171e293b5d78e46243061f0ff5f69a7f68923937
 size 6776