Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34f7c9f58b8006385995ced81e6445accf31a9b8a633aacfb0c70b92fc518b3e
+oid sha256:73a10ff5eb3169db4be2445ff7800df6ca56baf41d13df8beabc8dbd49758ae1
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf98b9dd13314e20beaff9f79e1eebccaea346aa82a3bf932061a8f81b389e7b
+oid sha256:2eae897c01400a9b8db73e8dccb20a5cf751422c61f8a0f8ea7fa2d6cb6a973b
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48f8f6135c7853ebe442ee7acd4ef9a904245becd61941f4c9ec59b6ead1f855
+oid sha256:8e0747b8c0f8a4ac9c7c69f279af311715abe07e1d91c1c29f20fdd8f88956b7
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e818f6fe93c49323bdb08dd60b51f7d49082edfe5fc12b2bfe83ab714f779a95
+oid sha256:3e82b50b2ea56f39b6747507c52624e7d162a635e82738b894c21d143ffb08c1
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 1000,
-  "best_metric": 2.22625994682312,
-  "best_model_checkpoint": "./outputs/checkpoint-1000",
-  "epoch": 1.0857763300760044,
+  "best_global_step": 1200,
+  "best_metric": 2.21370530128479,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.3029315960912053,
   "eval_steps": 200,
-  "global_step": 1000,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -188,6 +188,42 @@
       "eval_samples_per_second": 81.558,
       "eval_steps_per_second": 2.574,
       "step": 1000
+    },
+    {
+      "epoch": 1.1400651465798046,
+      "grad_norm": 0.788972795009613,
+      "learning_rate": 0.00014022534788594312,
+      "loss": 2.2099,
+      "step": 1050
+    },
+    {
+      "epoch": 1.1943539630836049,
+      "grad_norm": 0.7912983894348145,
+      "learning_rate": 0.00013486009898582889,
+      "loss": 2.1799,
+      "step": 1100
+    },
+    {
+      "epoch": 1.248642779587405,
+      "grad_norm": 0.766243040561676,
+      "learning_rate": 0.00012937802194741994,
+      "loss": 2.2058,
+      "step": 1150
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "grad_norm": 0.8190643191337585,
+      "learning_rate": 0.00012379748908958562,
+      "loss": 2.2021,
+      "step": 1200
+    },
+    {
+      "epoch": 1.3029315960912053,
+      "eval_loss": 2.21370530128479,
+      "eval_runtime": 7.3565,
+      "eval_samples_per_second": 81.833,
+      "eval_steps_per_second": 2.583,
+      "step": 1200
     }
   ],
   "logging_steps": 50,
@@ -216,7 +252,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.8005692620367462e+17,
+  "total_flos": 3.361352657491722e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null