Training in progress, step 100, checkpoint

last-checkpoint/adapter_config.json

@@ -16,7 +16,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 64,
+  "r": 128,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7f3e44220566d2fcc5f3a3e52c9431073b703a9d7c064edf8cb32732756c84
-size 80755416
+oid sha256:8323bb41f0aec0087583e20fb47f1106184860b835424bd34d1ab0f0a8fb2e4a
+size 161495976

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1226966392c0dc19149594b36ffa4fc40aafb874fba4f30ebe743fa8368f673b
-size 161549562
+oid sha256:71abd4ee1689a0f3666931b9c5222b04a6cc078f8ad0b4eb67220c7c4df7d150
+size 323030394

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb33dde475e37a38bbcbac0d77838dc8d3f56cd3ec4f50514a1a3cbeff6a2db
+oid sha256:7ce7ad989673c906fdcd6e022121c69b0bfbaf276dc65f9b1db64b337bf68bd9
 size 15920

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38d844c14592ca2f8291dc47c5e1a37a7cf773e040645e03846771a8691878b8
+oid sha256:611208056cc182e52b28fe74e4f36d5dfa0a63f0ab33e266388c668997363c82
 size 15920

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aeb729f5f5e53f0b47a52bef026d5be0dc6911a1f6277476a02cf3026a137aae
+oid sha256:2a341b5fded49e5cb6754db9d820c3110301cf8f8e71b36485f8e8fca1b6d78a
 size 15920

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6cc6d20901f5d88eaf9c346d5d39ddb8c3137a52ca887bd2a08f47465a4766
+oid sha256:13750c4d3886605197cece143409a5593d2c07bb2453a892059fe24939f3b224
 size 15920

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a8a3d7a3c6a692ced5f2b8a6c0361500df3e1ae20dc830289a3eceaa637aa4d
+oid sha256:06bc9b42f2606d7281cea26486e86497e0c21b8bdf62f336865c28ec62b108e8
 size 15920

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c7a9dc7b1c7fd441a8fba291d3fbecb9446d965c4af3bb9331630fb58c6abc4
+oid sha256:c3c532524540af574acd792d2fc1558a31467d0129abe13d3dc3100812066447
 size 15920

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e53ffdf7f17b0edb1206793f3f83762f79b39c4d8e0726d3c38a798fd2a1c7d
+oid sha256:42d0664307850defde5eb0a6a4c06f3bf6a5c44a33bf45757c2e88e8381b3e2b
 size 15920

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c44828b7d225ea6fb4eec9981294ef3fa29afc77cea8911ffeaceb934c92cd4
+oid sha256:0e37cce0d224b675329fd8792e5622b89473e3a5858b7a41f1125f4a92496ebc
 size 15920

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab256ad805e97aa6befdfa09ba9058e68832ed277b1113181e30378f969a4730
+oid sha256:4e19ad1f5d7f52daf3b72aeb69d7620865cdadf7b3b937a56cdfbd259a75f1fa
 size 1064

last-checkpoint/trainer_state.json

@@ -3,30 +3,22 @@
   "best_model_checkpoint": null,
   "epoch": 0.12012012012012012,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.06006006006006006,
-      "eval_loss": 0.979826807975769,
-      "eval_runtime": 2.4571,
-      "eval_samples_per_second": 13.023,
-      "eval_steps_per_second": 0.407,
-      "step": 100
-    },
     {
       "epoch": 0.12012012012012012,
-      "eval_loss": 0.34023797512054443,
-      "eval_runtime": 2.4552,
-      "eval_samples_per_second": 13.033,
-      "eval_steps_per_second": 0.407,
-      "step": 200
+      "eval_loss": 0.9743305444717407,
+      "eval_runtime": 2.4675,
+      "eval_samples_per_second": 12.969,
+      "eval_steps_per_second": 0.405,
+      "step": 100
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1665,
+  "max_steps": 832,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -42,7 +34,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9583689365127168e+17,
+  "total_flos": 1.961522215602094e+17,
   "train_batch_size": 4,
   "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:fad72378f0a04778ac3b7ad9629cc028106a87b8fc4da2040b5af9f21fd7f7a8
+oid sha256:1ad1e06e489682adc6b5971dafe89bf52490c96fab40f4ee6bd406626f79bc76
 size 5560