Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1893d174fc5f55f120c5d3ea3b7c7f2c4d2a38a52bfce7cc13d3e84b6a692d7f
+oid sha256:92ef1101cc9fb02e54282334b0e6bd4e60d0595cb559d42d57d36013d19881dd
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01b30a0c4d6db8d7f28a669b2be0c1378f787ed3a409c6cacd0be25b2b694c4c
+oid sha256:674c977647d24c2401ddc1a423df58aa831693103103edd9672feaafde0d28d5
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e40ea359638b52e758ceb9d32eefb338c627a16912fda7333840aa375be67f
+oid sha256:e709aa0555fa5194531caefe8b2d088ae3dbd38583b58f3fca70a67516efdf96
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79faef7859961c2a638e4312a796703fd0c86e5877b740a2ce8b47db225af025
+oid sha256:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
 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": 304.3478260869565,
+  "epoch": 326.0869565217391,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1099,6 +1099,84 @@
       "eval_samples_per_second": 12.175,
       "eval_steps_per_second": 1.588,
       "step": 7000
+    },
+    {
+      "epoch": 306.5217391304348,
+      "grad_norm": 0.8590102791786194,
+      "learning_rate": 1.5883333333333333e-06,
+      "loss": 0.4127,
+      "step": 7050
+    },
+    {
+      "epoch": 308.69565217391306,
+      "grad_norm": 0.9405089616775513,
+      "learning_rate": 1.505e-06,
+      "loss": 0.413,
+      "step": 7100
+    },
+    {
+      "epoch": 310.8695652173913,
+      "grad_norm": 0.7493429780006409,
+      "learning_rate": 1.4216666666666667e-06,
+      "loss": 0.4137,
+      "step": 7150
+    },
+    {
+      "epoch": 313.04347826086956,
+      "grad_norm": 0.8461248278617859,
+      "learning_rate": 1.3383333333333334e-06,
+      "loss": 0.4104,
+      "step": 7200
+    },
+    {
+      "epoch": 315.2173913043478,
+      "grad_norm": 0.6727828979492188,
+      "learning_rate": 1.255e-06,
+      "loss": 0.4071,
+      "step": 7250
+    },
+    {
+      "epoch": 317.39130434782606,
+      "grad_norm": 0.7143705487251282,
+      "learning_rate": 1.1716666666666667e-06,
+      "loss": 0.4086,
+      "step": 7300
+    },
+    {
+      "epoch": 319.5652173913044,
+      "grad_norm": 0.8034409284591675,
+      "learning_rate": 1.0883333333333334e-06,
+      "loss": 0.4051,
+      "step": 7350
+    },
+    {
+      "epoch": 321.7391304347826,
+      "grad_norm": 0.7853546738624573,
+      "learning_rate": 1.0050000000000001e-06,
+      "loss": 0.4067,
+      "step": 7400
+    },
+    {
+      "epoch": 323.9130434782609,
+      "grad_norm": 0.8830783367156982,
+      "learning_rate": 9.216666666666667e-07,
+      "loss": 0.4089,
+      "step": 7450
+    },
+    {
+      "epoch": 326.0869565217391,
+      "grad_norm": 0.8115708231925964,
+      "learning_rate": 8.383333333333334e-07,
+      "loss": 0.4129,
+      "step": 7500
+    },
+    {
+      "epoch": 326.0869565217391,
+      "eval_loss": 0.4083060622215271,
+      "eval_runtime": 12.9398,
+      "eval_samples_per_second": 12.442,
+      "eval_steps_per_second": 1.623,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.483460821750851e+16,
+  "total_flos": 9.088988346445709e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null