Training in progress, step 2580, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99dae515fa23ad18fb5d804785a042044e88c12f664e33ed30799d995c9c0e2e
+oid sha256:fa10074e1d6ddc94d23153c9734747c8baf91d47d6dba6666b1ef724ab871f8c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3155003d2ea5cc790dee6fd194de467b7e81fb05ef1aa596c5a462da8a4bdbca
+oid sha256:d9ab1eb9cd7c1ea28ecdf3adae9b1c04bcbc49f42a37845326b6ae05057c7199
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49541cd98b68651da591e11bb8ee1a4d2340295f0f1855a2571126b55e63a83c
+oid sha256:66d8839ff66cb4b737720f4f9d1c90cc3202ad969b799aa3c2659a6ea5ff1a82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b81f5081497282279ac6e33fa4ff19b1cd4357d0b584f715bb3836bdeb5ad85
+oid sha256:42f27a730b6ee07b80f832c5a86ad2126ba907f4b4cf4aa2e99d8c5986c6b885
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9159212880143113,
+  "epoch": 0.9230769230769231,
   "eval_steps": 500,
-  "global_step": 2560,
+  "global_step": 2580,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2055,14 +2055,30 @@
       "loss": 0.3661,
       "num_input_tokens_seen": 1735842,
       "step": 2560
+    },
+    {
+      "epoch": 0.9194991055456172,
+      "grad_norm": 0.25310322642326355,
+      "learning_rate": 1.6100178890876567e-05,
+      "loss": 0.3926,
+      "num_input_tokens_seen": 1742027,
+      "step": 2570
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.32354310154914856,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 0.3949,
+      "num_input_tokens_seen": 1748817,
+      "step": 2580
     }
   ],
   "logging_steps": 10,
   "max_steps": 2795,
-  "num_input_tokens_seen": 1735842,
+  "num_input_tokens_seen": 1748817,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 3.903295664144794e+16,
+  "total_flos": 3.932471857163674e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null