Training in progress, step 3, checkpoint

last-checkpoint/adapter_config.json

@@ -20,15 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "gate_proj",
     "shared_expert_gate",
     "gate",
-    "down_proj",
+    "o_proj",
     "k_proj",
-    "v_proj",
-    "up_proj"
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "v_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 sha256:2ea4bc590a3f64abc18c6abca7ef01156731236a4007f9d9db1421462d3805be
+oid sha256:fd35864bd69b7f99459862c09297a4fd22715243bb5093e89a80098ec0684e16
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5da83df925a829b303ddccf3fd44a0556d27ab9a54b8346dd7035ea720fb4498
+oid sha256:1f06e6baaad70b74088cc936aab5abb89e700202afbde115abbd20a7bb3be7ae
 size 1324026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b625beb9586c12d3ef87f863627cf1db1b4a366bf34a26335b16b8495461534a
+oid sha256:b9af5373aa88895259568af4bb4ee43ae11bdbf1ba2f7d2b539d2b279040940d
 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": 0.004602991944764097,
+  "epoch": 0.001380897583429229,
   "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": 0.00046029919447640965,
-      "grad_norm": 0.6517150402069092,
+      "grad_norm": 0.6887022852897644,
       "learning_rate": 2e-05,
       "loss": 11.9193,
       "step": 1
@@ -18,97 +18,32 @@
     {
       "epoch": 0.00046029919447640965,
       "eval_loss": 11.924036979675293,
-      "eval_runtime": 61.8596,
-      "eval_samples_per_second": 14.792,
-      "eval_steps_per_second": 7.404,
+      "eval_runtime": 63.2544,
+      "eval_samples_per_second": 14.465,
+      "eval_steps_per_second": 7.241,
       "step": 1
     },
     {
       "epoch": 0.0009205983889528193,
-      "grad_norm": 0.6211732029914856,
+      "grad_norm": 0.6521114706993103,
       "learning_rate": 4e-05,
       "loss": 11.9113,
       "step": 2
     },
     {
       "epoch": 0.001380897583429229,
-      "grad_norm": 0.5110118985176086,
+      "grad_norm": 0.5372654795646667,
       "learning_rate": 6e-05,
-      "loss": 11.9381,
+      "loss": 11.9379,
       "step": 3
     },
     {
       "epoch": 0.001380897583429229,
-      "eval_loss": 11.923264503479004,
-      "eval_runtime": 61.1401,
-      "eval_samples_per_second": 14.966,
-      "eval_steps_per_second": 7.491,
+      "eval_loss": 11.923266410827637,
+      "eval_runtime": 62.2177,
+      "eval_samples_per_second": 14.706,
+      "eval_steps_per_second": 7.361,
       "step": 3
-    },
-    {
-      "epoch": 0.0018411967779056386,
-      "grad_norm": 0.7255784869194031,
-      "learning_rate": 8e-05,
-      "loss": 11.911,
-      "step": 4
-    },
-    {
-      "epoch": 0.0023014959723820483,
-      "grad_norm": 0.5302078723907471,
-      "learning_rate": 0.0001,
-      "loss": 11.9208,
-      "step": 5
-    },
-    {
-      "epoch": 0.002761795166858458,
-      "grad_norm": 0.6136360764503479,
-      "learning_rate": 0.00012,
-      "loss": 11.9207,
-      "step": 6
-    },
-    {
-      "epoch": 0.002761795166858458,
-      "eval_loss": 11.920000076293945,
-      "eval_runtime": 61.201,
-      "eval_samples_per_second": 14.951,
-      "eval_steps_per_second": 7.484,
-      "step": 6
-    },
-    {
-      "epoch": 0.003222094361334868,
-      "grad_norm": 0.4935219883918762,
-      "learning_rate": 0.00014,
-      "loss": 11.9358,
-      "step": 7
-    },
-    {
-      "epoch": 0.003682393555811277,
-      "grad_norm": 0.6514948606491089,
-      "learning_rate": 0.00016,
-      "loss": 11.9266,
-      "step": 8
-    },
-    {
-      "epoch": 0.004142692750287687,
-      "grad_norm": 0.6624245643615723,
-      "learning_rate": 0.00018,
-      "loss": 11.9153,
-      "step": 9
-    },
-    {
-      "epoch": 0.004142692750287687,
-      "eval_loss": 11.91427993774414,
-      "eval_runtime": 61.1185,
-      "eval_samples_per_second": 14.971,
-      "eval_steps_per_second": 7.494,
-      "step": 9
-    },
-    {
-      "epoch": 0.004602991944764097,
-      "grad_norm": 0.7241260409355164,
-      "learning_rate": 0.0002,
-      "loss": 11.9041,
-      "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": 10156108677120.0,
+  "total_flos": 3046832603136.0,
   "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:c31bb60baa41f0a49b9b6039c5f3fd7b89a212fd7da6c9fd4de1518f03732c2f
+oid sha256:d9da840bdb838bb97829663eb18e509c12561d7a78df1b5b8f4f2deaafbf53dc
 size 6776