Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d892c8f1d2ce54e5c87f641de0fae913556bb0ae64732b179df689e834e50648
+oid sha256:f3aee522a310439c9d8c9a42090dc4ba9d35c1104a743ac8b26c2a3fdf9f397a
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887c9b1370e8531c80797ba8b19eccb3f9816a8c038c1949cf758faada7a3846
+oid sha256:a5a6f7e6ba1906afe23e46eea98906d3ad11f3722309905c061a889da3669d9a
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd333563d341e5baa5c8b808fe012ad11a41788bafd15e1988d5d595a4760af
+oid sha256:13096529883c0adffb5e69839f0a1cd926efd800efac40df816e6ab444626905
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2413515687851971,
+  "epoch": 0.32180209171359614,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 376.693,
       "eval_steps_per_second": 189.784,
       "step": 75
+    },
+    {
+      "epoch": 0.24456958970233306,
+      "grad_norm": 0.0437646359205246,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 10.3828,
+      "step": 76
+    },
+    {
+      "epoch": 0.24778761061946902,
+      "grad_norm": 0.032487086951732635,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 10.3798,
+      "step": 77
+    },
+    {
+      "epoch": 0.251005631536605,
+      "grad_norm": 0.04608071595430374,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 10.3712,
+      "step": 78
+    },
+    {
+      "epoch": 0.25422365245374096,
+      "grad_norm": 0.056901391595602036,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 10.3763,
+      "step": 79
+    },
+    {
+      "epoch": 0.2574416733708769,
+      "grad_norm": 0.046913083642721176,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 10.3764,
+      "step": 80
+    },
+    {
+      "epoch": 0.2606596942880129,
+      "grad_norm": 0.052617162466049194,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 10.369,
+      "step": 81
+    },
+    {
+      "epoch": 0.26387771520514886,
+      "grad_norm": 0.05337031930685043,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.3717,
+      "step": 82
+    },
+    {
+      "epoch": 0.2670957361222848,
+      "grad_norm": 0.042702097445726395,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 10.3666,
+      "step": 83
+    },
+    {
+      "epoch": 0.27031375703942073,
+      "grad_norm": 0.05693927779793739,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 10.3707,
+      "step": 84
+    },
+    {
+      "epoch": 0.2735317779565567,
+      "grad_norm": 0.05402141436934471,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 10.3667,
+      "step": 85
+    },
+    {
+      "epoch": 0.27674979887369267,
+      "grad_norm": 0.0453721359372139,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 10.3705,
+      "step": 86
+    },
+    {
+      "epoch": 0.27996781979082863,
+      "grad_norm": 0.05169159919023514,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 10.3684,
+      "step": 87
+    },
+    {
+      "epoch": 0.2831858407079646,
+      "grad_norm": 0.036517977714538574,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 10.3798,
+      "step": 88
+    },
+    {
+      "epoch": 0.28640386162510056,
+      "grad_norm": 0.04753509908914566,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 10.3798,
+      "step": 89
+    },
+    {
+      "epoch": 0.28962188254223653,
+      "grad_norm": 0.0526588037610054,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 10.3766,
+      "step": 90
+    },
+    {
+      "epoch": 0.2928399034593725,
+      "grad_norm": 0.058646757155656815,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 10.367,
+      "step": 91
+    },
+    {
+      "epoch": 0.29605792437650846,
+      "grad_norm": 0.04773501679301262,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 10.3645,
+      "step": 92
+    },
+    {
+      "epoch": 0.29927594529364443,
+      "grad_norm": 0.04955429211258888,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 10.3743,
+      "step": 93
+    },
+    {
+      "epoch": 0.3024939662107804,
+      "grad_norm": 0.04964098334312439,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 10.382,
+      "step": 94
+    },
+    {
+      "epoch": 0.3057119871279163,
+      "grad_norm": 0.04339337348937988,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 10.3749,
+      "step": 95
+    },
+    {
+      "epoch": 0.3089300080450523,
+      "grad_norm": 0.048966653645038605,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 10.3647,
+      "step": 96
+    },
+    {
+      "epoch": 0.31214802896218824,
+      "grad_norm": 0.046769801527261734,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 10.3762,
+      "step": 97
+    },
+    {
+      "epoch": 0.3153660498793242,
+      "grad_norm": 0.04105059802532196,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 10.375,
+      "step": 98
+    },
+    {
+      "epoch": 0.3185840707964602,
+      "grad_norm": 0.06437543779611588,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 10.3682,
+      "step": 99
+    },
+    {
+      "epoch": 0.32180209171359614,
+      "grad_norm": 0.05633605644106865,
+      "learning_rate": 0.0,
+      "loss": 10.3867,
+      "step": 100
+    },
+    {
+      "epoch": 0.32180209171359614,
+      "eval_loss": 10.375041007995605,
+      "eval_runtime": 0.3463,
+      "eval_samples_per_second": 378.262,
+      "eval_steps_per_second": 190.575,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 969818112000.0,
+  "total_flos": 1293090816000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null