Training in progress, step 785, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:916f37872f2b282127854c113b88d7933e3c6c22deb3493dee6f2bb869c8dc81
+oid sha256:6e464c7891a3c35ceecd38f82390d8d7db9a5c03f0ce2449fd8fd5579a3eb307
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a45e4e480aaa7c81fec8584a873ce0efc9ecb9ce8e1ec028a2ec8faf12c27ec1
+oid sha256:bdbf1a5fb29d1decac72f6a37923552e9506adf101625e4a3447353186c4585f
 size 49846644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8566e721ef91b4bb0b82cb6023f5dd2184670c621b1104f02d62bf820375f9df
+oid sha256:ef3ee6b0c3abd49db5cf9ed927275682158ff63ad48c4ce36ddf29cba5344043
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a5479532bafb0d8dbf7d1cd4c9665f76912e36e4b505953c015533d8cac1f5d
+oid sha256:6fce68b4e0bd8cc627fa21933deded54c30243c0736d888455dfea939c5b032a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0093820769977353,
+  "epoch": 1.015852474927208,
   "eval_steps": 386,
-  "global_step": 780,
+  "global_step": 785,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5491,6 +5491,41 @@
       "learning_rate": 9.12121465400356e-05,
       "loss": 0.7507,
       "step": 780
+    },
+    {
+      "epoch": 1.01067615658363,
+      "grad_norm": 0.6894446611404419,
+      "learning_rate": 9.118878759911029e-05,
+      "loss": 0.8629,
+      "step": 781
+    },
+    {
+      "epoch": 1.0119702361695244,
+      "grad_norm": 0.8267707228660583,
+      "learning_rate": 9.116540065362338e-05,
+      "loss": 0.8126,
+      "step": 782
+    },
+    {
+      "epoch": 1.0132643157554189,
+      "grad_norm": 0.7307786345481873,
+      "learning_rate": 9.114198571947587e-05,
+      "loss": 0.729,
+      "step": 783
+    },
+    {
+      "epoch": 1.0145583953413135,
+      "grad_norm": 0.7283042669296265,
+      "learning_rate": 9.111854281258772e-05,
+      "loss": 0.8176,
+      "step": 784
+    },
+    {
+      "epoch": 1.015852474927208,
+      "grad_norm": 0.8333950042724609,
+      "learning_rate": 9.109507194889792e-05,
+      "loss": 0.8758,
+      "step": 785
     }
   ],
   "logging_steps": 1,
@@ -5510,7 +5545,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.719211228477522e+17,
+  "total_flos": 8.7751080870622e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null