Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab786f741c7a478f92cbba3fdd1ddd3a418946d605848f775e0f6c469c96daf4
+oid sha256:f649bc97ca842140ab28c612e0e561ebbde8139ce799f23e401fad5ec0bf673a
 size 29034840

last-checkpoint/global_step2900/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c680026b961d2af4d8531a1009d4325d4aee0011e5a4841d0f7be05d66ade814
+size 43429616

last-checkpoint/global_step2900/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42c3a0056f516a18f586cb0fd96b075cf6f88223a9519e3d05c1825c42854a5a
+size 43429616

last-checkpoint/global_step2900/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7fb00ae7f41df9fdb5bcfca5ae2a0ee34109a9526870c75e600273241aa2e9b
+size 43429616

last-checkpoint/global_step2900/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19fe721ba700619098cae1c23138a52aafaf176ecf1f46e7e63f24793a559f24
+size 43429616

last-checkpoint/global_step2900/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4450ed4bf964babed675fcd2ae59c712e01b319719ea4623b508e9e8bbfc354d
+size 637299

last-checkpoint/global_step2900/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac843c84f2c600b4501ddce6691d3bee44a437550b44b143970c70aa46ede7b9
+size 637171

last-checkpoint/global_step2900/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf16b94da5090df4fc41c6cb44c197f5c1e0eeef0b24cce4b8ff38d26ec7d36
+size 637171

last-checkpoint/global_step2900/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42703655a551b8b9d2fb71bb55d8aec753128d736359e443ff46543063b42daf
+size 637171

last-checkpoint/latest

@@ -1 +1 @@
-global_step2850
+global_step2900

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8dba2341c0517760edfde50521977f02a5bd982ffd3bc03de6109439c4f478
+oid sha256:ce92cea831a04716b4b472f1dad1cc986b2021dee9aac057217f5d455b27ec42
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2bf831df9fbade9ac2a8db79798bc2a7b1afb85a78a6e463ec7a7db4acc0f8e
+oid sha256:3cddb73bbdf0f6f6a2c3182d70f7ad5d587353b164c08dd4f383b940d6b61e4e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8602ff0a0fa366d46b61c0ef2b23ce468387898cf2bc1027e5450de73ddf647f
+oid sha256:b24b508e466beb446d37377d2a04757d3bc2b4230de3ac56b25a65d7753a74c1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bb51d675cf23603b1b765cd645f53d6b66ddb104d56d48674e9c798e086f696
+oid sha256:b4c6a18a7de8b25b21673ba2ff7efbaaae00ec8c453c7975b467c1df87b87022
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8784a806a517b57d5b84ca561594528563d0fdcdc4d0513f5b313f6cc716b68e
+oid sha256:6207ec0a6d3415bd88090ab549215521abec8051b511fdc1a1cfc0484ab44197
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.1869634985923767,
   "best_model_checkpoint": "saves/CADICA_qwenvl_direction_then_DetectAndClassify_scale6/lora/sft/checkpoint-2350",
-  "epoch": 0.8419497784342689,
+  "epoch": 0.8567208271787297,
   "eval_steps": 50,
-  "global_step": 2850,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5080,11 +5080,100 @@
       "eval_steps_per_second": 0.77,
       "num_input_tokens_seen": 29600536,
       "step": 2850
+    },
+    {
+      "epoch": 0.843426883308715,
+      "grad_norm": 1.4547945162774674,
+      "learning_rate": 6.675498736513036e-05,
+      "loss": 0.2163,
+      "num_input_tokens_seen": 29652440,
+      "step": 2855
+    },
+    {
+      "epoch": 0.844903988183161,
+      "grad_norm": 1.3348915008279034,
+      "learning_rate": 6.663987164217236e-05,
+      "loss": 0.2589,
+      "num_input_tokens_seen": 29704376,
+      "step": 2860
+    },
+    {
+      "epoch": 0.8463810930576071,
+      "grad_norm": 2.2889038673998603,
+      "learning_rate": 6.652465664590703e-05,
+      "loss": 0.2325,
+      "num_input_tokens_seen": 29756504,
+      "step": 2865
+    },
+    {
+      "epoch": 0.8478581979320532,
+      "grad_norm": 1.3144459851000174,
+      "learning_rate": 6.640934306370586e-05,
+      "loss": 0.242,
+      "num_input_tokens_seen": 29807328,
+      "step": 2870
+    },
+    {
+      "epoch": 0.8493353028064993,
+      "grad_norm": 1.2238000417554058,
+      "learning_rate": 6.629393158352854e-05,
+      "loss": 0.2169,
+      "num_input_tokens_seen": 29859208,
+      "step": 2875
+    },
+    {
+      "epoch": 0.8508124076809453,
+      "grad_norm": 1.5853683051276755,
+      "learning_rate": 6.61784228939188e-05,
+      "loss": 0.2335,
+      "num_input_tokens_seen": 29911128,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8522895125553914,
+      "grad_norm": 0.8463095817606877,
+      "learning_rate": 6.606281768400032e-05,
+      "loss": 0.1913,
+      "num_input_tokens_seen": 29962384,
+      "step": 2885
+    },
+    {
+      "epoch": 0.8537666174298375,
+      "grad_norm": 1.6841064365294203,
+      "learning_rate": 6.594711664347264e-05,
+      "loss": 0.2425,
+      "num_input_tokens_seen": 30013664,
+      "step": 2890
+    },
+    {
+      "epoch": 0.8552437223042836,
+      "grad_norm": 1.1559578384960632,
+      "learning_rate": 6.5831320462607e-05,
+      "loss": 0.2312,
+      "num_input_tokens_seen": 30066016,
+      "step": 2895
+    },
+    {
+      "epoch": 0.8567208271787297,
+      "grad_norm": 0.9327537302615286,
+      "learning_rate": 6.571542983224223e-05,
+      "loss": 0.2029,
+      "num_input_tokens_seen": 30118072,
+      "step": 2900
+    },
+    {
+      "epoch": 0.8567208271787297,
+      "eval_loss": 0.39434579014778137,
+      "eval_runtime": 19.1253,
+      "eval_samples_per_second": 3.137,
+      "eval_steps_per_second": 0.784,
+      "num_input_tokens_seen": 30118072,
+      "step": 2900
     }
   ],
   "logging_steps": 5,
   "max_steps": 6770,
-  "num_input_tokens_seen": 29600536,
+  "num_input_tokens_seen": 30118072,
   "num_train_epochs": 2,
   "save_steps": 50,
   "stateful_callbacks": {
@@ -5099,7 +5188,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1952800415416320.0,
+  "total_flos": 1986962888589312.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null