Training in progress, step 70, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91af94eb4c5415d1a468c9b94c24f6f4eb665b5e18798cc0709c272b261e4b01
+oid sha256:c9149805fd0ff6c9295a21f0ceed866ec5e19b987dc9b024c5713996cbccee03
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9a0ed33acc4b1549d8d32d9a92007a622c069ce765f2bb5b27b3224b50e48fa
+oid sha256:4e2f761486d2d2277401dace4f44681830fd254ea3d41966c9a17c77fec745aa
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45fa2328ce571cd92a5087de8545d212e2efaf113a696e08cab907cc8ae2b386
+oid sha256:4abd8c451028780b83d24be580224b85633dd02b3c6970e7c2e5f6a76f5c96a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5747c56edca12686176331b1c30c5158c6a70283eb79bb7b20753e8e93d73f7
+oid sha256:34cc44421081656693b70701aad2c568b7fd366e841bbfc436ac5b6eb6c2b321
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.597938144329897,
+  "epoch": 2.88659793814433,
   "eval_steps": 7,
-  "global_step": 63,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -234,6 +234,28 @@
       "eval_samples_per_second": 13.589,
       "eval_steps_per_second": 1.989,
       "step": 63
+    },
+    {
+      "epoch": 2.7216494845360826,
+      "grad_norm": 1.3034956455230713,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.8017,
+      "step": 66
+    },
+    {
+      "epoch": 2.845360824742268,
+      "grad_norm": 1.2311569452285767,
+      "learning_rate": 9.913756075728087e-07,
+      "loss": 0.8266,
+      "step": 69
+    },
+    {
+      "epoch": 2.88659793814433,
+      "eval_loss": 1.205170750617981,
+      "eval_runtime": 3.0134,
+      "eval_samples_per_second": 13.606,
+      "eval_steps_per_second": 1.991,
+      "step": 70
     }
   ],
   "logging_steps": 3,
@@ -253,7 +275,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.301411817639117e+16,
+  "total_flos": 1.0340054014623744e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null