Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1071652c84ae8cff079bacf083815e29a2c6ce551b00dcf67c37b264fc624e77
+oid sha256:4f443882242ddbd40941209e4a0e6877bf6a845e499c111ee7646474bc2d5d67
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c345fef49cd111d959a45fa7def0661f57b9a328cf327bf439db1ce039df3a3b
+oid sha256:7e048ad67b3266263900fe71524be3e7dc7a47780658388e5d17114aae41ff4d
 size 168155346

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af90d9bd53ef6e01e741f740accadc59008352f0e7d7bbe666104823a9634cc6
+oid sha256:61499f823566f61d141610b35eff248a50a427b5e7b93ed444e378c82d3f7bf9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:520939a2b861396046dd9c00e1116122d631161038719e48262b93fdca69303b
+oid sha256:c7b5bf190dc871967c45091d9f1ab233b2d2ed62baca21fee5dfedb5718ffa5d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2161431948665991,
+  "epoch": 0.2701789935832489,
   "eval_steps": 1000,
-  "global_step": 800,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,6 +127,42 @@
       "learning_rate": 2.339555568810221e-05,
       "loss": 0.8341,
       "step": 800
+    },
+    {
+      "epoch": 0.22965214454576158,
+      "grad_norm": 1.3319884538650513,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.8472,
+      "step": 850
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 1.5228185653686523,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.8233,
+      "step": 900
+    },
+    {
+      "epoch": 0.25667004390408643,
+      "grad_norm": 1.154761791229248,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.8262,
+      "step": 950
+    },
+    {
+      "epoch": 0.2701789935832489,
+      "grad_norm": 1.1170167922973633,
+      "learning_rate": 0.0,
+      "loss": 0.8293,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2701789935832489,
+      "eval_loss": 0.8305127024650574,
+      "eval_runtime": 807.4769,
+      "eval_samples_per_second": 7.72,
+      "eval_steps_per_second": 0.966,
+      "step": 1000
     }
   ],
   "logging_steps": 50,
@@ -141,12 +177,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.246236390400721e+18,
+  "total_flos": 1.5573330969388646e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null