Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "v_proj",
-    "o_proj",
     "q_proj",
+    "gate_proj",
     "down_proj",
-    "k_proj",
-    "up_proj"
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "k_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 sha256:5db3abd5a201fb8356842ffc5a5dbbefaaca6f8e62c43cf08c43de5053ee2767
+oid sha256:d91b65fceb4ee7e0dbc51f9dd1859bd3711fbda0529dff585cd0569d3881aa93
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b823e68111ccab962d0c3ec377b48babb90048b5bbc2c631e240768c6487987a
+oid sha256:132f4d3612b09c60d896bf45f2a95b035777dbcf4d248cbcad6ae3b7d47dce95
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580a78039b006147c49fed961f84593aff50f8571d4e98d9723902082cb2076d
+oid sha256:86b1d1c847833c161251571b388af565d36854d60391836c815a5c304e314a4b
 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": 0.010269576379974325,
+  "epoch": 0.0030808729139922978,
   "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": 0.0010269576379974327,
-      "grad_norm": 6.075960159301758,
+      "grad_norm": 6.53356409072876,
       "learning_rate": 2e-05,
       "loss": 10.0927,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.0010269576379974327,
       "eval_loss": 10.528717994689941,
-      "eval_runtime": 4.5132,
-      "eval_samples_per_second": 90.844,
-      "eval_steps_per_second": 45.422,
+      "eval_runtime": 4.1743,
+      "eval_samples_per_second": 98.22,
+      "eval_steps_per_second": 49.11,
       "step": 1
     },
     {
       "epoch": 0.0020539152759948653,
-      "grad_norm": 6.781851291656494,
+      "grad_norm": 7.160462379455566,
       "learning_rate": 4e-05,
       "loss": 10.5907,
       "step": 2
     },
     {
       "epoch": 0.0030808729139922978,
-      "grad_norm": 6.434222221374512,
+      "grad_norm": 6.975811958312988,
       "learning_rate": 6e-05,
-      "loss": 10.899,
+      "loss": 10.8963,
       "step": 3
     },
     {
       "epoch": 0.0030808729139922978,
-      "eval_loss": 10.519669532775879,
-      "eval_runtime": 4.5866,
-      "eval_samples_per_second": 89.392,
-      "eval_steps_per_second": 44.696,
+      "eval_loss": 10.518180847167969,
+      "eval_runtime": 4.1966,
+      "eval_samples_per_second": 97.699,
+      "eval_steps_per_second": 48.849,
       "step": 3
-    },
-    {
-      "epoch": 0.004107830551989731,
-      "grad_norm": 6.141213417053223,
-      "learning_rate": 8e-05,
-      "loss": 10.4349,
-      "step": 4
-    },
-    {
-      "epoch": 0.005134788189987163,
-      "grad_norm": 6.231571197509766,
-      "learning_rate": 0.0001,
-      "loss": 10.3238,
-      "step": 5
-    },
-    {
-      "epoch": 0.0061617458279845955,
-      "grad_norm": 6.933601379394531,
-      "learning_rate": 0.00012,
-      "loss": 10.3417,
-      "step": 6
-    },
-    {
-      "epoch": 0.0061617458279845955,
-      "eval_loss": 10.377058029174805,
-      "eval_runtime": 4.5181,
-      "eval_samples_per_second": 90.747,
-      "eval_steps_per_second": 45.373,
-      "step": 6
-    },
-    {
-      "epoch": 0.007188703465982028,
-      "grad_norm": 6.134459495544434,
-      "learning_rate": 0.00014,
-      "loss": 10.1669,
-      "step": 7
-    },
-    {
-      "epoch": 0.008215661103979461,
-      "grad_norm": 6.5450544357299805,
-      "learning_rate": 0.00016,
-      "loss": 10.2532,
-      "step": 8
-    },
-    {
-      "epoch": 0.009242618741976894,
-      "grad_norm": 6.545663356781006,
-      "learning_rate": 0.00018,
-      "loss": 10.3762,
-      "step": 9
-    },
-    {
-      "epoch": 0.009242618741976894,
-      "eval_loss": 10.074318885803223,
-      "eval_runtime": 4.5925,
-      "eval_samples_per_second": 89.275,
-      "eval_steps_per_second": 44.638,
-      "step": 9
-    },
-    {
-      "epoch": 0.010269576379974325,
-      "grad_norm": 6.369472503662109,
-      "learning_rate": 0.0002,
-      "loss": 10.3033,
-      "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": 655585443840.0,
+  "total_flos": 196675633152.0,
   "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:eb3cc866d9a89376abfe965f141857d18b67bd14074b0ff70e3e13586641604e
+oid sha256:bc6b76bc8346177b062e0773e35362faa66be22d69bdb8c16896f639c6e3ff36
 size 6776