Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd6982bcc60cdab0257c5094b578ba6dd17785574ecd91ea21df18552dbdab50
+oid sha256:5611d10b1dc80593a4bdac7adf240fe7ec3afb8b0341077ac9b221743431d240
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4face8b726be5cd04943e9e5f20c0e41d61b0080a239c9e4a48e0b8cdbc1597e
+oid sha256:fddc7e913fccc4858d959218eae2f6aac98fe04277ee85b74657756755ab2870
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95cf693139e04c01121688b12511c05f9de3f56de464e2930cb3c2286f2d7b73
+oid sha256:33fe29649d802f7d8ce4e623123929a93b4808eb8a2c328e1a109d7a9f4c467e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66bcaad5c279053510b4367912ea249c63fe5414f054543836bf0c249b07d43a
+oid sha256:5bb902d188125a4ef066dade0a74ca2e9fa70cf1044624b225dbb2185e85ddda
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236d7d0f7ffc1a0e9f5b2e6c786ad0abef19806ab482f50f3f227b962f635dcd
+oid sha256:200267047c5b4a65eb479d595575902edeb4e9007b7178ed9fed04b9d89d7e3e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028469750889679714,
+  "epoch": 0.05693950177935943,
   "eval_steps": 4,
-  "global_step": 4,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -51,6 +51,42 @@
       "eval_samples_per_second": 32.886,
       "eval_steps_per_second": 4.163,
       "step": 4
+    },
+    {
+      "epoch": 0.03558718861209965,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.042704626334519574,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.0498220640569395,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.05693950177935943,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.05693950177935943,
+      "eval_loss": NaN,
+      "eval_runtime": 7.1934,
+      "eval_samples_per_second": 32.947,
+      "eval_steps_per_second": 4.171,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -70,7 +106,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1870196536967168e+16,
+  "total_flos": 2.3740393073934336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null