Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ef1101cc9fb02e54282334b0e6bd4e60d0595cb559d42d57d36013d19881dd
+oid sha256:e4f5b7eb731d80ba7fa9e08897112adb60df70410cb7a191fbe80df3ce92be45
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:674c977647d24c2401ddc1a423df58aa831693103103edd9672feaafde0d28d5
+oid sha256:e18fafcf0c0f3815c420b1c31b14b9f4a7ec7554f4991ab26e1bed8d170f3d2f
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e709aa0555fa5194531caefe8b2d088ae3dbd38583b58f3fca70a67516efdf96
+oid sha256:519f4775ca84a56cc7e5f6f0fb76a2348e31326ce758c1c51c986b8abb151d12
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
+oid sha256:0aef1303f298e810b9c563fac5650fcaebc5d5e2a568db30104db374f503c826
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.40593138337135315,
   "best_model_checkpoint": "mikhail_panzo/zlm-fil_b64_le5_s8000/checkpoint-7000",
-  "epoch": 326.0869565217391,
+  "epoch": 347.82608695652175,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 12.442,
       "eval_steps_per_second": 1.623,
       "step": 7500
+    },
+    {
+      "epoch": 328.2608695652174,
+      "grad_norm": 0.6245155334472656,
+      "learning_rate": 7.550000000000001e-07,
+      "loss": 0.4067,
+      "step": 7550
+    },
+    {
+      "epoch": 330.4347826086956,
+      "grad_norm": 0.7212103009223938,
+      "learning_rate": 6.716666666666668e-07,
+      "loss": 0.4038,
+      "step": 7600
+    },
+    {
+      "epoch": 332.60869565217394,
+      "grad_norm": 0.8665474057197571,
+      "learning_rate": 5.883333333333333e-07,
+      "loss": 0.4048,
+      "step": 7650
+    },
+    {
+      "epoch": 334.7826086956522,
+      "grad_norm": 0.7773168087005615,
+      "learning_rate": 5.05e-07,
+      "loss": 0.4054,
+      "step": 7700
+    },
+    {
+      "epoch": 336.95652173913044,
+      "grad_norm": 0.7131752967834473,
+      "learning_rate": 4.2166666666666667e-07,
+      "loss": 0.4058,
+      "step": 7750
+    },
+    {
+      "epoch": 339.1304347826087,
+      "grad_norm": 0.7420967221260071,
+      "learning_rate": 3.3833333333333336e-07,
+      "loss": 0.409,
+      "step": 7800
+    },
+    {
+      "epoch": 341.30434782608694,
+      "grad_norm": 0.866454541683197,
+      "learning_rate": 2.55e-07,
+      "loss": 0.4071,
+      "step": 7850
+    },
+    {
+      "epoch": 343.4782608695652,
+      "grad_norm": 0.6852492094039917,
+      "learning_rate": 1.7166666666666668e-07,
+      "loss": 0.4054,
+      "step": 7900
+    },
+    {
+      "epoch": 345.6521739130435,
+      "grad_norm": 0.8399931788444519,
+      "learning_rate": 8.833333333333334e-08,
+      "loss": 0.4033,
+      "step": 7950
+    },
+    {
+      "epoch": 347.82608695652175,
+      "grad_norm": 0.8192908763885498,
+      "learning_rate": 5e-09,
+      "loss": 0.4035,
+      "step": 8000
+    },
+    {
+      "epoch": 347.82608695652175,
+      "eval_loss": 0.40772464871406555,
+      "eval_runtime": 13.1445,
+      "eval_samples_per_second": 12.248,
+      "eval_steps_per_second": 1.598,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.088988346445709e+16,
+  "total_flos": 9.695483990986939e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null