Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca60095f86e48a89c115bed3de4d6e6d51ec2903783fab00ce19205817f38c5
+oid sha256:d9b20be4465fc9f2fdc45a6b03c5b94b7d02f5beb0c6ee41705041ee2fa42bb1
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67a4bb936e346a4b958bd78c0646fdd71067c03febe3739e01fb6f283bec2fc9
+oid sha256:a89a4dd12c905f92cb01197f96241d3b525490721258224cc4c8522e1e53dc47
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79277a227d1f9ed20ed2b76370b7fe6a60007b66c24329b5335340d05b155313
+oid sha256:9373077514cae46a49373636d8533017b0efe6437cb3126984a56adfa969ea82
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
+oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,56 +2,177 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1,
-  "eval_steps": 20,
-  "global_step": 20,
+  "epoch": 0.5,
+  "eval_steps": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.11081302911043167,
+      "grad_norm": 0.10900866985321045,
       "learning_rate": 1.6e-06,
-      "loss": 11.017050170898438,
+      "loss": 11.06564712524414,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.1046549528837204,
+      "grad_norm": 0.10152705758810043,
       "learning_rate": 3.6e-06,
-      "loss": 11.006002807617188,
+      "loss": 11.040735626220703,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.1001407653093338,
+      "grad_norm": 0.09875829517841339,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 10.999064636230468,
+      "loss": 11.026320648193359,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.10080653429031372,
+      "grad_norm": 0.09957622736692429,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 10.995188903808593,
+      "loss": 11.012971496582031,
       "step": 20
     },
     {
-      "epoch": 0.1,
-      "eval_accuracy": 1.7094017094017095e-05,
-      "eval_loss": 10.983185768127441,
-      "eval_runtime": 91.7452,
-      "eval_samples_per_second": 10.9,
-      "eval_steps_per_second": 1.82,
-      "step": 20
+      "epoch": 0.125,
+      "grad_norm": 0.1074257642030716,
+      "learning_rate": 3.9466531944960116e-06,
+      "loss": 10.992045593261718,
+      "step": 25
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.110373854637146,
+      "learning_rate": 3.902113032590307e-06,
+      "loss": 10.97699432373047,
+      "step": 30
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 0.11517436057329178,
+      "learning_rate": 3.844579509954769e-06,
+      "loss": 10.947827911376953,
+      "step": 35
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.1078442707657814,
+      "learning_rate": 3.7744456388872234e-06,
+      "loss": 10.949494171142579,
+      "step": 40
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 0.1252269148826599,
+      "learning_rate": 3.6921905048418706e-06,
+      "loss": 10.916586303710938,
+      "step": 45
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.12218247354030609,
+      "learning_rate": 3.598375993789849e-06,
+      "loss": 10.902359008789062,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.001978021978021978,
+      "eval_loss": 10.892147064208984,
+      "eval_runtime": 11.0414,
+      "eval_samples_per_second": 9.057,
+      "eval_steps_per_second": 1.54,
+      "step": 50
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 0.12842494249343872,
+      "learning_rate": 3.4936429539683075e-06,
+      "loss": 10.880451202392578,
+      "step": 55
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.12605500221252441,
+      "learning_rate": 3.3787068182371314e-06,
+      "loss": 10.865975952148437,
+      "step": 60
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 0.12930333614349365,
+      "learning_rate": 3.254352716947074e-06,
+      "loss": 10.846955871582031,
+      "step": 65
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.1300428807735443,
+      "learning_rate": 3.1214301147033453e-06,
+      "loss": 10.831236267089844,
+      "step": 70
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.13403981924057007,
+      "learning_rate": 2.9808470076610163e-06,
+      "loss": 10.815153503417969,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.1414586752653122,
+      "learning_rate": 2.833563720990581e-06,
+      "loss": 10.798695373535157,
+      "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.1405540555715561,
+      "learning_rate": 2.680586348883286e-06,
+      "loss": 10.79158706665039,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.15637332201004028,
+      "learning_rate": 2.5229598819076393e-06,
+      "loss": 10.773637390136718,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.15481412410736084,
+      "learning_rate": 2.36176106866422e-06,
+      "loss": 10.747270965576172,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1801270991563797,
+      "learning_rate": 2.198091060500926e-06,
+      "loss": 10.725272369384765,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.032405372405372404,
+      "eval_loss": 10.71803092956543,
+      "eval_runtime": 10.5701,
+      "eval_samples_per_second": 9.461,
+      "eval_steps_per_second": 1.608,
+      "step": 100
     }
   ],
   "logging_steps": 5,
   "max_steps": 200,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9223372036854775807,
-  "save_steps": 20,
+  "save_steps": 100,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b0b6058a46bce4b387df0ce8c61d4b0b1b316ccf92487321cd86eb8514ad352
+oid sha256:917d0d97de493b58757e5f74362d60fd58076fa34ab6735a0440935a012608ef
 size 5265