Training in progress, step 6, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f4a808bd67186d7d670e4b2906f3abad9a64c53bca704ef674f7fb9fbafe356
+oid sha256:0fd5bd3088c9dc6d4270b4593b6aeda089b938f7aded2a24ef05fc559a49af34
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b05e382a0dc585a1edddaa3981f4516a2749fb31ef358641805de2c253630
+oid sha256:c8d4a9970cd45f83995f7935ca4181e3edca1b6c8bab0d236ce8cd236c94ea84
 size 97487290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad03281210143d9b425d68b803482d2d514057ab8f987b89392de2b79cdb25d0
+oid sha256:c6cd39cdb37120f55361cd5e0069f61be89d255f23a8450b4d3163474d73427f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,16 +1,16 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018793459875963165,
+  "epoch": 0.0011276075925577898,
   "eval_steps": 3,
-  "global_step": 10,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.00018793459875963165,
-      "grad_norm": 0.41265636682510376,
+      "grad_norm": 0.4121508002281189,
       "learning_rate": 2e-05,
       "loss": 2.0097,
       "step": 1
@@ -18,97 +18,61 @@
     {
       "epoch": 0.00018793459875963165,
       "eval_loss": 2.225860595703125,
-      "eval_runtime": 59.1454,
-      "eval_samples_per_second": 18.953,
-      "eval_steps_per_second": 18.953,
+      "eval_runtime": 104.6968,
+      "eval_samples_per_second": 10.707,
+      "eval_steps_per_second": 10.707,
       "step": 1
     },
     {
       "epoch": 0.0003758691975192633,
-      "grad_norm": 0.34109458327293396,
+      "grad_norm": 0.34095901250839233,
       "learning_rate": 4e-05,
       "loss": 2.0424,
       "step": 2
     },
     {
       "epoch": 0.0005638037962788949,
-      "grad_norm": 0.4408990442752838,
+      "grad_norm": 0.4388081431388855,
       "learning_rate": 6e-05,
       "loss": 2.2435,
       "step": 3
     },
     {
       "epoch": 0.0005638037962788949,
-      "eval_loss": 2.2232234477996826,
-      "eval_runtime": 53.5686,
-      "eval_samples_per_second": 20.926,
-      "eval_steps_per_second": 20.926,
+      "eval_loss": 2.2231271266937256,
+      "eval_runtime": 105.4847,
+      "eval_samples_per_second": 10.627,
+      "eval_steps_per_second": 10.627,
       "step": 3
     },
     {
       "epoch": 0.0007517383950385266,
-      "grad_norm": 0.3058125972747803,
+      "grad_norm": 0.3048204183578491,
       "learning_rate": 8e-05,
-      "loss": 2.1183,
+      "loss": 2.1182,
       "step": 4
     },
     {
       "epoch": 0.0009396729937981583,
-      "grad_norm": 0.44318097829818726,
+      "grad_norm": 0.4445512592792511,
       "learning_rate": 0.0001,
       "loss": 2.2092,
       "step": 5
     },
     {
       "epoch": 0.0011276075925577898,
-      "grad_norm": 0.3183535933494568,
+      "grad_norm": 0.3167805075645447,
       "learning_rate": 0.00012,
-      "loss": 2.2227,
+      "loss": 2.2226,
       "step": 6
     },
     {
       "epoch": 0.0011276075925577898,
-      "eval_loss": 2.2024617195129395,
-      "eval_runtime": 54.1467,
-      "eval_samples_per_second": 20.703,
-      "eval_steps_per_second": 20.703,
+      "eval_loss": 2.202314615249634,
+      "eval_runtime": 104.9224,
+      "eval_samples_per_second": 10.684,
+      "eval_steps_per_second": 10.684,
       "step": 6
-    },
-    {
-      "epoch": 0.0013155421913174216,
-      "grad_norm": 0.4959358274936676,
-      "learning_rate": 0.00014,
-      "loss": 2.1984,
-      "step": 7
-    },
-    {
-      "epoch": 0.0015034767900770532,
-      "grad_norm": 0.3904803693294525,
-      "learning_rate": 0.00016,
-      "loss": 2.1435,
-      "step": 8
-    },
-    {
-      "epoch": 0.001691411388836685,
-      "grad_norm": 0.3693416714668274,
-      "learning_rate": 0.00018,
-      "loss": 2.0586,
-      "step": 9
-    },
-    {
-      "epoch": 0.001691411388836685,
-      "eval_loss": 2.149339437484741,
-      "eval_runtime": 52.9676,
-      "eval_samples_per_second": 21.164,
-      "eval_steps_per_second": 21.164,
-      "step": 9
-    },
-    {
-      "epoch": 0.0018793459875963165,
-      "grad_norm": 0.36688560247421265,
-      "learning_rate": 0.0002,
-      "loss": 2.0788,
-      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -123,12 +87,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 695723045683200.0,
+  "total_flos": 417433827409920.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66aba1548284fb45544c3c449ae78c0d06cde4d353a7cacc54939951423f8e9a
+oid sha256:abb88f4cc1adc89d4050bb1bb8aee4d5e2999228bec3f38fcda07d103361cace
 size 6776