Training in progress, epoch 1, checkpoint

checkpoint-915/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 2,
+  "<s>": 1,
+  "<unk>": 0
+}

checkpoint-915/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cee7f728265b413bb4a7fa8e6fca0a886a59fbd0a05534a161abace1dca98375
+oid sha256:85850f73fe42b935575bd9f9159ef32b7adb078b09c4f656de58b4972ac15b5e
 size 54740293

checkpoint-915/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d13fc5ffc36bef005766528591e80914c61ac396f2d01de54f19d259496d333
+oid sha256:b204eabb575525c34359f5be9488174857980b0da9ffd9aa26562b425fe66864
 size 14575

checkpoint-915/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797ab517854af5d0271612dd0d3f991cd2a975e012e034aa25db504c9b22c43d
+oid sha256:b83c76e68e9f66d469d97aa3790e7338dcdbd435d98195ec6ef04a09070a183e
 size 627

checkpoint-915/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-915/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_metric": NaN,
-  "best_model_checkpoint": "./Mistral/07-12-23-mistralai-Mistral-7B-v0.1_multilang-dataset-3.0.3-portuguese-2_epochs-1_batch_2/checkpoints/checkpoint-915",
+  "best_model_checkpoint": "./Zeroshot/07-12-23-mistralai-Mistral-7B-v0.1_test-tensorboard-2_epochs-1_batch_2/checkpoints/checkpoint-915",
   "epoch": 1.0,
   "eval_steps": 500,
   "global_step": 915,
@@ -10,16 +10,16 @@
   "log_history": [
     {
       "epoch": 0.55,
-      "learning_rate": 0.0002026719920227699,
-      "loss": 267.2109,
+      "learning_rate": 0.02026719920227699,
+      "loss": 248.6968,
       "step": 500
     },
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 393.8494,
-      "eval_samples_per_second": 8.257,
-      "eval_steps_per_second": 0.518,
+      "eval_runtime": 412.6247,
+      "eval_samples_per_second": 7.881,
+      "eval_steps_per_second": 0.494,
       "step": 915
     }
   ],
@@ -27,7 +27,7 @@
   "max_steps": 915,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 6.206687759435366e+17,
+  "total_flos": 6.144165716414054e+17,
   "trial_name": null,
   "trial_params": null
 }

checkpoint-915/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be2683609287dd8e6db197c4b0ae992b704980dafb7a8e2594371a18b4d109c
-size 4411
+oid sha256:86147cf2d59bdcf5a9b45947aafa93c9c868b350879c7081d3dafade8d0a5c1e
+size 4347