Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1bc01c778b42cc791b60515d7b8df3b2ad215dd48b8d3bcd6a139ca85ba01c
+oid sha256:79471e688252e3a48b366caf5b00da4c8287cbbc12ce134bc37532e28b8fb07f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3e9bba34d1df05cf472654a3cab8317d5dd667f50ba514eaead9beaf5c1756
+oid sha256:ef8b83afe9bd63c19febea689fd6ed6c0d341aafdbc84c30e5fe2cd13b5a8d46
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d7098ecc6bd0d11a452e4a15810826462ebab0b93e505a69e1011b262a8265f
+oid sha256:c42d4a99df91dcb2725bdd7effbeb06036832b0ca054c032cc94b28425ecaec4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab098d97568c94b26c087e3ff4fd649c3aaa775049e6dbf18e927dde2c5feee8
+oid sha256:06829946ff807c7143728448cc1bf384944e638865601317db4b29a92003bb11
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010040160642570281,
+  "epoch": 0.020080321285140562,
   "eval_steps": 2,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,65 @@
       "learning_rate": 0.0001,
       "loss": 5.6033,
       "step": 5
+    },
+    {
+      "epoch": 0.012048192771084338,
+      "grad_norm": 1.0273263454437256,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 6.2224,
+      "step": 6
+    },
+    {
+      "epoch": 0.012048192771084338,
+      "eval_loss": 1.514455795288086,
+      "eval_runtime": 11.9707,
+      "eval_samples_per_second": 17.543,
+      "eval_steps_per_second": 8.771,
+      "step": 6
+    },
+    {
+      "epoch": 0.014056224899598393,
+      "grad_norm": 0.7513625025749207,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 5.5897,
+      "step": 7
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "grad_norm": 0.9003206491470337,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 5.6233,
+      "step": 8
+    },
+    {
+      "epoch": 0.01606425702811245,
+      "eval_loss": 1.4975639581680298,
+      "eval_runtime": 11.8994,
+      "eval_samples_per_second": 17.648,
+      "eval_steps_per_second": 8.824,
+      "step": 8
+    },
+    {
+      "epoch": 0.018072289156626505,
+      "grad_norm": 0.8670149445533752,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.0963,
+      "step": 9
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "grad_norm": 1.8713542222976685,
+      "learning_rate": 5e-05,
+      "loss": 5.4797,
+      "step": 10
+    },
+    {
+      "epoch": 0.020080321285140562,
+      "eval_loss": 1.4782865047454834,
+      "eval_runtime": 11.9189,
+      "eval_samples_per_second": 17.619,
+      "eval_steps_per_second": 8.81,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -85,7 +144,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1791624166244352.0,
+  "total_flos": 3501810870386688.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null