Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aac60fa61b1371f0628e4cdce110bd39a12e57e9c460d701427e8c58e754e7e9
+oid sha256:34f7c9f58b8006385995ced81e6445accf31a9b8a633aacfb0c70b92fc518b3e
 size 69782384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63b11235c95638e0ee559b2345b5d8f7a103f5995eca48cb715fe2ba2cac47e
+oid sha256:bf98b9dd13314e20beaff9f79e1eebccaea346aa82a3bf932061a8f81b389e7b
 size 139790651

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0516b0656c487c351bad1057295186b5e3e00c79529207cd235ce5be6a5d40
+oid sha256:48f8f6135c7853ebe442ee7acd4ef9a904245becd61941f4c9ec59b6ead1f855
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f1426694c38acbbdcb00f1a570a9712c4816b9dc6fb937a5303ba759aa3ab7
+oid sha256:e818f6fe93c49323bdb08dd60b51f7d49082edfe5fc12b2bfe83ab714f779a95
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 800,
-  "best_metric": 2.2396719455718994,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.8686210640608035,
+  "best_global_step": 1000,
+  "best_metric": 2.22625994682312,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.0857763300760044,
   "eval_steps": 200,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -152,6 +152,42 @@
       "eval_samples_per_second": 81.898,
       "eval_steps_per_second": 2.585,
       "step": 800
+    },
+    {
+      "epoch": 0.9229098805646037,
+      "grad_norm": 0.6467435359954834,
+      "learning_rate": 0.0001601655739753613,
+      "loss": 2.2523,
+      "step": 850
+    },
+    {
+      "epoch": 0.9771986970684039,
+      "grad_norm": 0.6962546706199646,
+      "learning_rate": 0.0001554426355793363,
+      "loss": 2.2509,
+      "step": 900
+    },
+    {
+      "epoch": 1.0314875135722041,
+      "grad_norm": 0.6648530960083008,
+      "learning_rate": 0.0001505338899112344,
+      "loss": 2.2103,
+      "step": 950
+    },
+    {
+      "epoch": 1.0857763300760044,
+      "grad_norm": 0.9022650122642517,
+      "learning_rate": 0.00014545578786002178,
+      "loss": 2.1862,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0857763300760044,
+      "eval_loss": 2.22625994682312,
+      "eval_runtime": 7.3813,
+      "eval_samples_per_second": 81.558,
+      "eval_steps_per_second": 2.574,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -180,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2399365411628646e+17,
+  "total_flos": 2.8005692620367462e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null