Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ef5b32a8a62931908755623e87d3799e1ace0bcc5a82ca5b0cb42f174abf39b
+oid sha256:e69508337a093a7ee674ee4f741f99f139e7e2c78c1be36764b9dab376fd4bd7
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148884d6c7ff51efadcf36692dc5ec40e8973c725d4ff1efefd7557427a285d8
+oid sha256:beb1ab69a22370510ed83d21fff5fe9b8dba6fa8c167d9db8a96afeea218c646
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4060886c8f06325a105271f5ee9d3973327355c66ff72bbab33ee261ed68656
+oid sha256:21a88e7a58b8640e03fbaf438f47d12780b3ac5b0439ebe7d26d20d40495b231
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41639d1994829bc2ee2cf4bcf82d4fb746380cad20e3d593102982ecf4be7313
+oid sha256:65e7f2a492ba0fc6e11860baa88e4ba1026051d3cc228ccacdaf47de2a669a24
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6253100633621216,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 1.6090008020401,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3114754098360657,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,27 @@
       "eval_samples_per_second": 43.721,
       "eval_steps_per_second": 5.47,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 1.5992,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 1.6090008020401,
+      "eval_runtime": 143.4499,
+      "eval_samples_per_second": 43.737,
+      "eval_steps_per_second": 5.472,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0124498798727168e+17,
+  "total_flos": 1.0719202477481165e+17,
   "trial_name": null,
   "trial_params": null
 }